diff --git a/src/PaddleClas/test_tipc/README.md b/src/PaddleClas/test_tipc/README.md new file mode 100644 index 0000000..4869f6e --- /dev/null +++ b/src/PaddleClas/test_tipc/README.md @@ -0,0 +1,108 @@ + +# 飞桨训推一体认证 + +## 1. 简介 + +飞桨除了基本的模型训练和预测，还提供了支持多端多平台的高性能推理部署工具。本文档提供了PaddleClas中所有模型的飞桨训推一体认证 (Training and Inference Pipeline Certification(TIPC)) 信息和测试工具，方便用户查阅每种模型的训练推理部署打通情况，并可以进行一键测试。 + +
+ +
+ +## 2. 汇总信息 + +打通情况汇总如下，已填写的部分表示可以使用本工具进行一键测试，未填写的表示正在支持中。 + +**字段说明：** +- 基础训练预测：包括模型训练、Paddle Inference Python预测。 +- 更多训练方式：包括多机多卡、混合精度。 +- 模型压缩：包括裁剪、离线/在线量化、蒸馏。 +- 其他预测部署：包括Paddle Inference C++预测、Paddle Serving部署、Paddle-Lite部署等。 + +更详细的mkldnn、Tensorrt等预测加速相关功能的支持情况可以查看各测试工具的[更多教程](#more)。 +| 算法论文 | 模型名称 | 模型类型 | 基础
训练预测 | 更多
训练方式 | 模型压缩 | 其他预测部署 | +| :--- | :--- | :----: | :--------: | :---- | :---- | :---- | +| ResNet |ResNet50_vd | 分类 | 支持 | 多机多卡
混合精度 | FPGM裁剪
PACT量化| | +| MobileNetV3 |MobileNetV3_large_x1_0 | 分类 | 支持 | 多机多卡
混合精度 | FPGM裁剪
PACT量化| | +| PPLCNet |PPLCNet_x2_5 | 分类 | 支持 | 多机多卡
混合精度 | - | | + +## 3. 测试工具简介 +### 目录介绍 +``` +./test_tipc/ +├── common_func.sh #test_*.sh会调用到的公共函数 +├── config # 配置文件目录 +│ ├── MobileNetV3 # MobileNetV3系列模型测试配置文件目录 +│ │ ├── MobileNetV3_large_x1_0_train_infer_python.txt #基础训练预测配置文件 +│ │ ├── MobileNetV3_large_x1_0_train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt #多机多卡训练预测配置文件 +│ │ └── MobileNetV3_large_x1_0_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt #混合精度训练预测配置文件 +│ └── ResNet # ResNet系列模型测试配置文件目录 +│ ├── ResNet50_vd_train_infer_python.txt #基础训练预测配置文件 +│ ├── ResNet50_vd_train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt #多机多卡训练预测配置文件 +│ └── ResNet50_vd_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt #混合精度训练预测配置文件 +| ...... +├── docs +│ ├── guide.png +│ └── test.png +├── prepare.sh # 完成test_*.sh运行所需要的数据和模型下载 +├── README.md # 使用文档 +├── results # 预先保存的预测结果，用于和实际预测结果进行精读比对 +└── test_train_inference_python.sh # 测试python训练预测的主程序 +``` + +### 测试流程概述 +使用本工具，可以测试不同功能的支持情况，以及预测结果是否对齐，测试流程如下： +
+ +
+ +1. 运行`prepare.sh`准备测试所需数据和模型； +2. 运行要测试的功能对应的测试脚本`test_*.sh`，产出log，由log可以看到不同配置是否运行成功； +3. 用`compare_results.py`对比log中的预测结果和预存在results目录下的结果，判断预测精度是否符合预期（在误差范围内）。 + +测试单项功能仅需两行命令，**如需测试不同模型/功能，替换配置文件即可**，命令格式如下： + +```shell +# 功能：准备数据 +# 格式：bash + 运行脚本 + 参数1: 配置文件选择 + 参数2: 模式选择 +bash test_tipc/prepare.sh configs/[model_name]/[params_file_name] [Mode] + +# 功能：运行测试 +# 格式：bash + 运行脚本 + 参数1: 配置文件选择 + 参数2: 模式选择 +bash test_tipc/test_train_inference_python.sh configs/[model_name]/[params_file_name] [Mode] + +``` + +例如，测试基本训练预测功能的`lite_train_lite_infer`模式，运行： + +```shell +# 准备数据 +bash test_tipc/prepare.sh ./test_tipc/configs/MobileNetV3/MobileNetV3_large_x1_0_train_infer_python.txt 'lite_train_lite_infer' +# 运行测试 +bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/MobileNetV3/MobileNetV3_large_x1_0_train_infer_python.txt 'lite_train_lite_infer' + +``` + +关于本示例命令的更多信息可查看[基础训练预测使用文档](docs/test_train_inference_python.md)。 + +### 配置文件命名规范 + +在`configs`目录下，**按模型系列划分为子目录**，子目录中存放所有该模型系列测试需要用到的配置文件，如`MobileNetV3`文件夹下存放了所有`MobileNetV3`系列模型的配置文件。配置文件的命名遵循如下规范： + +1. 基础训练预测配置简单命名为：`ModelName_train_infer_python.txt`，表示**Linux环境下单机、不使用混合精度训练+python预测**，其完整命名对应`ModelName_train_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt`，由于本配置文件使用频率较高，这里进行了名称简化。其中`ModelName`指具体模型名称 +2. 其他带训练配置命名格式为：`ModelName_train_训练硬件环境(linux_gpu/linux_dcu/…)_是否多机(fleet/normal)_是否混合精度(amp/normal)_预测模式(infer/lite/serving/js)_语言(cpp/python/java)_预测硬件环境(ModelName_linux_gpu/mac/jetson/opencl_arm_gpu/...).txt`。如，linux gpu下多机多卡+混合精度链条测试对应配置 `ModelName_train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt`，linux dcu下基础训练预测对应配置 `ModelName_train_linux_dcu_normal_normal_infer_python_linux_dcu.txt`。 +3. 仅预测的配置（如serving、lite等）命名格式：`ModelName_model_训练硬件环境(ModelName_linux_gpu/linux_dcu/…)_是否多机(fleet/normal)_是否混合精度(amp/normal)_(infer/lite/serving/js)_语言(cpp/python/java)_预测硬件环境(ModelName_linux_gpu/mac/jetson/opencl_arm_gpu/...).txt`，即，与2相比，仅第二个字段从train换为model，测试时模型直接下载获取，这里的“训练硬件环境”表示所测试的模型是在哪种环境下训练得到的。 + +**根据上述命名规范，可以直接从子目录名称和配置文件名找到需要测试的场景和功能对应的配置文件。** + + + +## 4 开始测试 + +各功能测试中涉及混合精度、裁剪、量化等训练相关，及mkldnn、Tensorrt等多种预测相关参数配置，请点击下方相应链接了解更多细节和使用教程： + +- [test_train_inference_python 使用](docs/test_train_inference_python.md)：测试基于Python的模型训练、评估、推理等基本功能，包括裁剪、量化、蒸馏。 +- [test_inference_cpp 使用](docs/test_inference_cpp.md) ：测试基于C++的模型推理。 +- [test_serving 使用](docs/test_serving.md) ：测试基于Paddle Serving的服务化部署功能。 +- [test_lite_arm_cpu_cpp 使用](docs/test_lite_arm_cpu_cpp.md): 测试基于Paddle-Lite的ARM CPU端c++预测部署功能. +- [test_paddle2onnx 使用](docs/test_paddle2onnx.md)：测试Paddle2ONNX的模型转化功能，并验证正确性。 diff --git a/src/PaddleClas/test_tipc/common_func.sh b/src/PaddleClas/test_tipc/common_func.sh new file mode 100644 index 0000000..3f0fa66 --- /dev/null +++ b/src/PaddleClas/test_tipc/common_func.sh @@ -0,0 +1,65 @@ +#!/bin/bash + +function func_parser_key(){ + strs=$1 + IFS=":" + array=(${strs}) + tmp=${array[0]} + echo ${tmp} +} + +function func_parser_value(){ + strs=$1 + IFS=":" + array=(${strs}) + tmp=${array[1]} + echo ${tmp} +} + +function func_set_params(){ + key=$1 + value=$2 + if [ ${key}x = "null"x ];then + echo " " + elif [[ ${value} = "null" ]] || [[ ${value} = " " ]] || [ ${#value} -le 0 ];then + echo " " + else + echo "${key}=${value}" + fi +} + +function func_parser_params(){ + strs=$1 + IFS=":" + array=(${strs}) + key=${array[0]} + tmp=${array[1]} + IFS="|" + res="" + for _params in ${tmp[*]}; do + IFS="=" + array=(${_params}) + mode=${array[0]} + value=${array[1]} + if [[ ${mode} = ${MODE} ]]; then + IFS="|" + #echo $(func_set_params "${mode}" "${value}") + echo $value + break + fi + IFS="|" + done + echo ${res} +} + +function status_check(){ + last_status=$1 # the exit code + run_command=$2 + run_log=$3 + if [ $last_status -eq 0 ]; then + echo -e "\033[33m Run successfully with command - ${run_command}! \033[0m" | tee -a ${run_log} + else + echo -e "\033[33m Run failed with command - ${run_command}! \033[0m" | tee -a ${run_log} + fi +} + diff --git a/src/PaddleClas/test_tipc/compare_results.py b/src/PaddleClas/test_tipc/compare_results.py new file mode 100644 index 0000000..e28410e --- /dev/null +++ b/src/PaddleClas/test_tipc/compare_results.py @@ -0,0 +1,140 @@ +import numpy as np +import os +import subprocess +import json +import argparse +import glob + + +def init_args(): + parser = argparse.ArgumentParser() + # params for testing assert allclose + parser.add_argument("--atol", type=float, default=1e-3) + parser.add_argument("--rtol", type=float, default=1e-3) + parser.add_argument("--gt_file", type=str, default="") + parser.add_argument("--log_file", type=str, default="") + parser.add_argument("--precision", type=str, default="fp32") + return parser + + +def parse_args(): + parser = init_args() + return parser.parse_args() + + +def run_shell_command(cmd): + p = subprocess.Popen( + cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True) + out, err = p.communicate() + + if p.returncode == 0: + return out.decode('utf-8') + else: + return None + + +def parser_results_from_log_by_name(log_path, names_list): + if not os.path.exists(log_path): + raise ValueError("The log file {} does not exists!".format(log_path)) + + if names_list is None or len(names_list) < 1: + return [] + + parser_results = {} + for name in names_list: + cmd = "grep {} {}".format(name, log_path) + outs = run_shell_command(cmd) + outs = outs.split("\n")[0] + result = outs.split("{}".format(name))[-1] + try: + result = json.loads(result) + except: + result = np.array([int(r) for r in result.split()]).reshape(-1, 4) + parser_results[name] = result + return parser_results + + +def load_gt_from_file(gt_file): + if not os.path.exists(gt_file): + raise ValueError("The log file {} does not exists!".format(gt_file)) + with open(gt_file, 'r') as f: + data = f.readlines() + f.close() + parser_gt = {} + for line in data: + image_name, result = line.strip("\n").split("\t") + image_name = image_name.split('/')[-1] + try: + result = json.loads(result) + except: + result = np.array([int(r) for r in result.split()]).reshape(-1, 4) + parser_gt[image_name] = result + return parser_gt + + +def load_gt_from_txts(gt_file): + gt_list = glob.glob(gt_file) + gt_collection = {} + for gt_f in gt_list: + gt_dict = load_gt_from_file(gt_f) + basename = os.path.basename(gt_f) + if "fp32" in basename: + gt_collection["fp32"] = [gt_dict, gt_f] + elif "fp16" in basename: + gt_collection["fp16"] = [gt_dict, gt_f] + elif "int8" in basename: + gt_collection["int8"] = [gt_dict, gt_f] + else: + continue + return gt_collection + + +def collect_predict_from_logs(log_path, key_list): + log_list = glob.glob(log_path) + pred_collection = {} + for log_f in log_list: + pred_dict = parser_results_from_log_by_name(log_f, key_list) + key = os.path.basename(log_f) + pred_collection[key] = pred_dict + + return pred_collection + + +def testing_assert_allclose(dict_x, dict_y, atol=1e-7, rtol=1e-7): + for k in dict_x: + np.testing.assert_allclose( + np.array(dict_x[k]), np.array(dict_y[k]), atol=atol, rtol=rtol) + + +if __name__ == "__main__": + # Usage: + # python3.7 tests/compare_results.py --gt_file=./tests/results/*.txt --log_file=./tests/output/infer_*.log + + args = parse_args() + + gt_collection = load_gt_from_txts(args.gt_file) + key_list = gt_collection["fp32"][0].keys() + + pred_collection = collect_predict_from_logs(args.log_file, key_list) + for filename in pred_collection.keys(): + if "fp32" in filename: + gt_dict, gt_filename = gt_collection["fp32"] + elif "fp16" in filename: + gt_dict, gt_filename = gt_collection["fp16"] + elif "int8" in filename: + gt_dict, gt_filename = gt_collection["int8"] + else: + continue + pred_dict = pred_collection[filename] + + try: + testing_assert_allclose( + gt_dict, pred_dict, atol=args.atol, rtol=args.rtol) + print( + "Assert allclose passed! The results of {} and {} are consistent!". + format(filename, gt_filename)) + except Exception as E: + print(E) + raise ValueError( + "The results of {} and the results of {} are inconsistent!". + format(filename, gt_filename)) diff --git a/src/PaddleClas/test_tipc/config/AlexNet/AlexNet_train_infer_python.txt b/src/PaddleClas/test_tipc/config/AlexNet/AlexNet_train_infer_python.txt new file mode 100644 index 0000000..7662f5d --- /dev/null +++ b/src/PaddleClas/test_tipc/config/AlexNet/AlexNet_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:AlexNet +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/AlexNet/AlexNet.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/AlexNet/AlexNet.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/AlexNet/AlexNet.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/AlexNet_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/CSPNet/CSPDarkNet53_train_infer_python.txt b/src/PaddleClas/test_tipc/config/CSPNet/CSPDarkNet53_train_infer_python.txt new file mode 100644 index 0000000..cd5ec06 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/CSPNet/CSPDarkNet53_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:CSPDarkNet53 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/CSPNet/CSPDarkNet53.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/CSPNet/CSPDarkNet53.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/CSPNet/CSPDarkNet53.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/CSPDarkNet53_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=288 -o PreProcess.transform_ops.1.CropImage.size=256 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DLA/DLA102_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DLA/DLA102_train_infer_python.txt new file mode 100644 index 0000000..0a85e2a --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DLA/DLA102_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DLA102 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DLA/DLA102.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DLA/DLA102.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DLA/DLA102.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DLA102_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DLA/DLA102x2_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DLA/DLA102x2_train_infer_python.txt new file mode 100644 index 0000000..fff0ee1 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DLA/DLA102x2_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DLA102x2 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DLA/DLA102x2.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DLA/DLA102x2.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DLA/DLA102x2.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DLA102x2_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DLA/DLA102x_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DLA/DLA102x_train_infer_python.txt new file mode 100644 index 0000000..db7af68 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DLA/DLA102x_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DLA102x +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DLA/DLA102x.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DLA/DLA102x.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DLA/DLA102x.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DLA102x_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DLA/DLA169_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DLA/DLA169_train_infer_python.txt new file mode 100644 index 0000000..0abc0e2 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DLA/DLA169_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DLA169 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DLA/DLA169.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DLA/DLA169.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DLA/DLA169.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DLA169_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DLA/DLA34_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DLA/DLA34_train_infer_python.txt new file mode 100644 index 0000000..fa06405 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DLA/DLA34_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DLA34 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DLA/DLA34.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DLA/DLA34.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DLA/DLA34.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DLA34_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DLA/DLA46_c_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DLA/DLA46_c_train_infer_python.txt new file mode 100644 index 0000000..8503452 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DLA/DLA46_c_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DLA46_c +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DLA/DLA46_c.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DLA/DLA46_c.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DLA/DLA46_c.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DLA46_c_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DLA/DLA46x_c_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DLA/DLA46x_c_train_infer_python.txt new file mode 100644 index 0000000..ee6c58a --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DLA/DLA46x_c_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DLA46x_c +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DLA/DLA46x_c.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DLA/DLA46x_c.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DLA/DLA46x_c.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DLA46x_c_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DLA/DLA60_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DLA/DLA60_train_infer_python.txt new file mode 100644 index 0000000..e14fcab --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DLA/DLA60_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DLA60 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DLA/DLA60.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DLA/DLA60.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DLA/DLA60.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DLA60_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DLA/DLA60x_c_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DLA/DLA60x_c_train_infer_python.txt new file mode 100644 index 0000000..cd45206 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DLA/DLA60x_c_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DLA60x_c +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DLA/DLA60x_c.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DLA/DLA60x_c.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DLA/DLA60x_c.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DLA60x_c_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DLA/DLA60x_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DLA/DLA60x_train_infer_python.txt new file mode 100644 index 0000000..51b7e77 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DLA/DLA60x_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DLA60x +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DLA/DLA60x.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DLA/DLA60x.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DLA/DLA60x.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DLA60x_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DPN/DPN107_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DPN/DPN107_train_infer_python.txt new file mode 100644 index 0000000..646bce3 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DPN/DPN107_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DPN107 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DPN/DPN107.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DPN/DPN107.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DPN/DPN107.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DPN107_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DPN/DPN131_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DPN/DPN131_train_infer_python.txt new file mode 100644 index 0000000..1aaea6a --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DPN/DPN131_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DPN131 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DPN/DPN131.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DPN/DPN131.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DPN/DPN131.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DPN131_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DPN/DPN68_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DPN/DPN68_train_infer_python.txt new file mode 100644 index 0000000..d26e5e3 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DPN/DPN68_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DPN68 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DPN/DPN68.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DPN/DPN68.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DPN/DPN68.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DPN68_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DPN/DPN92_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DPN/DPN92_train_infer_python.txt new file mode 100644 index 0000000..3d0d077 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DPN/DPN92_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DPN92 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DPN/DPN92.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DPN/DPN92.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DPN/DPN92.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DPN92_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DPN/DPN98_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DPN/DPN98_train_infer_python.txt new file mode 100644 index 0000000..e4cee43 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DPN/DPN98_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DPN98 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DPN/DPN98.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DPN/DPN98.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DPN/DPN98.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DPN98_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DarkNet/DarkNet53_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DarkNet/DarkNet53_train_infer_python.txt new file mode 100644 index 0000000..b10918e --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DarkNet/DarkNet53_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DarkNet53 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DarkNet/DarkNet53.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DarkNet/DarkNet53.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DarkNet/DarkNet53.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DarkNet53_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=292 -o PreProcess.transform_ops.1.CropImage.size=256 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DeiT/DeiT_base_patch16_224_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DeiT/DeiT_base_patch16_224_train_infer_python.txt new file mode 100644 index 0000000..d10fc20 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DeiT/DeiT_base_patch16_224_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DeiT_base_patch16_224 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DeiT/DeiT_base_patch16_224.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DeiT/DeiT_base_patch16_224.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DeiT/DeiT_base_patch16_224.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DeiT_base_patch16_224_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DeiT/DeiT_base_patch16_384_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DeiT/DeiT_base_patch16_384_train_infer_python.txt new file mode 100644 index 0000000..c8fc60e --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DeiT/DeiT_base_patch16_384_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DeiT_base_patch16_384 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DeiT/DeiT_base_patch16_384.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DeiT/DeiT_base_patch16_384.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DeiT/DeiT_base_patch16_384.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DeiT_base_patch16_384_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=384 -o PreProcess.transform_ops.1.CropImage.size=384 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DeiT/DeiT_small_patch16_224_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DeiT/DeiT_small_patch16_224_train_infer_python.txt new file mode 100644 index 0000000..83ea4c3 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DeiT/DeiT_small_patch16_224_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DeiT_small_patch16_224 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DeiT/DeiT_small_patch16_224.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DeiT/DeiT_small_patch16_224.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DeiT/DeiT_small_patch16_224.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DeiT_small_patch16_224_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DeiT/DeiT_tiny_patch16_224_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DeiT/DeiT_tiny_patch16_224_train_infer_python.txt new file mode 100644 index 0000000..cb18502 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DeiT/DeiT_tiny_patch16_224_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DeiT_tiny_patch16_224 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DeiT/DeiT_tiny_patch16_224.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DeiT/DeiT_tiny_patch16_224.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DeiT/DeiT_tiny_patch16_224.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DeiT_tiny_patch16_224_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DenseNet/DenseNet121_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DenseNet/DenseNet121_train_infer_python.txt new file mode 100644 index 0000000..9f89e4c --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DenseNet/DenseNet121_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DenseNet121 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DenseNet/DenseNet121.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DenseNet/DenseNet121.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DenseNet/DenseNet121.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DenseNet121_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DenseNet/DenseNet161_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DenseNet/DenseNet161_train_infer_python.txt new file mode 100644 index 0000000..379cc29 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DenseNet/DenseNet161_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DenseNet161 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DenseNet/DenseNet161.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DenseNet/DenseNet161.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DenseNet/DenseNet161.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DenseNet161_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DenseNet/DenseNet169_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DenseNet/DenseNet169_train_infer_python.txt new file mode 100644 index 0000000..c2e2bbb --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DenseNet/DenseNet169_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DenseNet169 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DenseNet/DenseNet169.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DenseNet/DenseNet169.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DenseNet/DenseNet169.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DenseNet169_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DenseNet/DenseNet201_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DenseNet/DenseNet201_train_infer_python.txt new file mode 100644 index 0000000..08dedc4 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DenseNet/DenseNet201_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DenseNet201 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DenseNet/DenseNet201.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DenseNet/DenseNet201.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DenseNet/DenseNet201.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DenseNet201_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/DenseNet/DenseNet264_train_infer_python.txt b/src/PaddleClas/test_tipc/config/DenseNet/DenseNet264_train_infer_python.txt new file mode 100644 index 0000000..146ad68 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/DenseNet/DenseNet264_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:DenseNet264 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/DenseNet/DenseNet264.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/DenseNet/DenseNet264.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/DenseNet/DenseNet264.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DenseNet264_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ESNet/ESNet_x0_25_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ESNet/ESNet_x0_25_train_infer_python.txt new file mode 100644 index 0000000..82ead10 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ESNet/ESNet_x0_25_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ESNet_x0_25 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ESNet/ESNet_x0_25.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ESNet/ESNet_x0_25.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ESNet/ESNet_x0_25.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ESNet_x0_25_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ESNet/ESNet_x0_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ESNet/ESNet_x0_5_train_infer_python.txt new file mode 100644 index 0000000..38b376f --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ESNet/ESNet_x0_5_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ESNet_x0_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ESNet/ESNet_x0_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ESNet/ESNet_x0_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ESNet/ESNet_x0_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ESNet_x0_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ESNet/ESNet_x0_75_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ESNet/ESNet_x0_75_train_infer_python.txt new file mode 100644 index 0000000..dc63498 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ESNet/ESNet_x0_75_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ESNet_x0_75 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ESNet/ESNet_x0_75.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ESNet/ESNet_x0_75.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ESNet/ESNet_x0_75.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ESNet_x0_75_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ESNet/ESNet_x1_0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ESNet/ESNet_x1_0_train_infer_python.txt new file mode 100644 index 0000000..c5a4a5a --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ESNet/ESNet_x1_0_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ESNet_x1_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ESNet/ESNet_x1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ESNet/ESNet_x1_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ESNet/ESNet_x1_0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ESNet_x1_0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB0_train_infer_python.txt new file mode 100644 index 0000000..23b3ef1 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB0_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:EfficientNetB0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/EfficientNetB0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB1_train_infer_python.txt b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB1_train_infer_python.txt new file mode 100644 index 0000000..1c43145 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB1_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:EfficientNetB1 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB1.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB1.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB1.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/EfficientNetB1_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=272 -o PreProcess.transform_ops.1.CropImage.size=240 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB2_train_infer_python.txt b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB2_train_infer_python.txt new file mode 100644 index 0000000..0ac16c3 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB2_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:EfficientNetB2 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB2.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB2.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB2.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/EfficientNetB2_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=292 -o PreProcess.transform_ops.1.CropImage.size=260 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB3_train_infer_python.txt b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB3_train_infer_python.txt new file mode 100644 index 0000000..0d0ca3d --- /dev/null +++ b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB3_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:EfficientNetB3 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB3.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB3.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB3.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/EfficientNetB3_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=332 -o PreProcess.transform_ops.1.CropImage.size=300 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB4_train_infer_python.txt b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB4_train_infer_python.txt new file mode 100644 index 0000000..92d4cb8 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB4_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:EfficientNetB4 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB4.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB4.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB4.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/EfficientNetB4_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=412 -o PreProcess.transform_ops.1.CropImage.size=380 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB5_train_infer_python.txt new file mode 100644 index 0000000..02c9357 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB5_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:EfficientNetB5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/EfficientNetB5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=488 -o PreProcess.transform_ops.1.CropImage.size=456 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB6_train_infer_python.txt b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB6_train_infer_python.txt new file mode 100644 index 0000000..392c048 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB6_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:EfficientNetB6 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:2 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB6.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB6.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB6.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/EfficientNetB6_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=560 -o PreProcess.transform_ops.1.CropImage.size=528 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB7_train_infer_python.txt b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB7_train_infer_python.txt new file mode 100644 index 0000000..7265243 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/EfficientNet/EfficientNetB7_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:EfficientNetB7 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:2 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB7.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB7.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/EfficientNet/EfficientNetB7.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/EfficientNetB7_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=632 -o PreProcess.transform_ops.1.CropImage.size=600 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_custom_sampler.txt b/src/PaddleClas/test_tipc/config/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_custom_sampler.txt new file mode 100644 index 0000000..c1dbc89 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_custom_sampler.txt @@ -0,0 +1,27 @@ +===========================train_params=========================== +model_name:GeneralRecognition_PPLCNet_x2_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5.yaml -o DataLoader.Train.sampler.name="PKSampler" -o DataLoader.Train.sampler.sample_per_id=2 +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:null +null:null +## + diff --git a/src/PaddleClas/test_tipc/config/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_infer_python.txt new file mode 100644 index 0000000..40e6675 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:GeneralRecognition_PPLCNet_x2_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/pretrain/general_PPLCNet_x2_5_pretrained_v1.0.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_rec.py -c configs/inference_rec.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.rec_inference_model_dir:../inference +-o Global.infer_imgs:../dataset/Aliproduct/demo_test/ +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_multicard_eval.txt b/src/PaddleClas/test_tipc/config/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_multicard_eval.txt new file mode 100644 index 0000000..165cfa9 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_multicard_eval.txt @@ -0,0 +1,26 @@ +===========================train_params=========================== +model_name:GeneralRecognition_PPLCNet_x2_5 +python:python3.7 +gpu_list:0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:null +null:null +## diff --git a/src/PaddleClas/test_tipc/config/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_no_eval.txt b/src/PaddleClas/test_tipc/config/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_no_eval.txt new file mode 100644 index 0000000..1e16751 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_no_eval.txt @@ -0,0 +1,26 @@ +===========================train_params=========================== +model_name:GeneralRecognition_PPLCNet_x2_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.eval_during_train=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:null +null:null +## diff --git a/src/PaddleClas/test_tipc/config/GhostNet/GhostNet_x0_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/GhostNet/GhostNet_x0_5_train_infer_python.txt new file mode 100644 index 0000000..7df8dee --- /dev/null +++ b/src/PaddleClas/test_tipc/config/GhostNet/GhostNet_x0_5_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:GhostNet_x0_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/GhostNet/GhostNet_x0_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/GhostNet/GhostNet_x0_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/GhostNet/GhostNet_x0_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/GhostNet_x0_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/GhostNet/GhostNet_x1_0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/GhostNet/GhostNet_x1_0_train_infer_python.txt new file mode 100644 index 0000000..7d3184b --- /dev/null +++ b/src/PaddleClas/test_tipc/config/GhostNet/GhostNet_x1_0_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:GhostNet_x1_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/GhostNet/GhostNet_x1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/GhostNet/GhostNet_x1_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/GhostNet/GhostNet_x1_0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/GhostNet_x1_0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/GhostNet/GhostNet_x1_3_train_infer_python.txt b/src/PaddleClas/test_tipc/config/GhostNet/GhostNet_x1_3_train_infer_python.txt new file mode 100644 index 0000000..e186eea --- /dev/null +++ b/src/PaddleClas/test_tipc/config/GhostNet/GhostNet_x1_3_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:GhostNet_x1_3 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/GhostNet/GhostNet_x1_3.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/GhostNet/GhostNet_x1_3.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/GhostNet/GhostNet_x1_3.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/GhostNet_x1_3_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/HRNet/HRNet_W18_C_train_infer_python.txt b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W18_C_train_infer_python.txt new file mode 100644 index 0000000..3883580 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W18_C_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:HRNet_W18_C +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/HRNet/HRNet_W18_C.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/HRNet/HRNet_W18_C.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/HRNet/HRNet_W18_C.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/HRNet_W18_C_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/HRNet/HRNet_W30_C_train_infer_python.txt b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W30_C_train_infer_python.txt new file mode 100644 index 0000000..cba0265 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W30_C_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:HRNet_W30_C +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/HRNet/HRNet_W30_C.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/HRNet/HRNet_W30_C.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/HRNet/HRNet_W30_C.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/HRNet_W30_C_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/HRNet/HRNet_W32_C_train_infer_python.txt b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W32_C_train_infer_python.txt new file mode 100644 index 0000000..197a76b --- /dev/null +++ b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W32_C_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:HRNet_W32_C +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/HRNet/HRNet_W32_C.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/HRNet/HRNet_W32_C.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/HRNet/HRNet_W32_C.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/HRNet_W32_C_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/HRNet/HRNet_W40_C_train_infer_python.txt b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W40_C_train_infer_python.txt new file mode 100644 index 0000000..1deb891 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W40_C_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:HRNet_W40_C +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/HRNet/HRNet_W40_C.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/HRNet/HRNet_W40_C.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/HRNet/HRNet_W40_C.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/HRNet_W40_C_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/HRNet/HRNet_W44_C_train_infer_python.txt b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W44_C_train_infer_python.txt new file mode 100644 index 0000000..10fab3d --- /dev/null +++ b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W44_C_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:HRNet_W44_C +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/HRNet/HRNet_W44_C.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/HRNet/HRNet_W44_C.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/HRNet/HRNet_W44_C.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/HRNet_W44_C_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/HRNet/HRNet_W48_C_train_infer_python.txt b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W48_C_train_infer_python.txt new file mode 100644 index 0000000..6de8e26 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W48_C_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:HRNet_W48_C +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/HRNet/HRNet_W48_C.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/HRNet/HRNet_W48_C.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/HRNet/HRNet_W48_C.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/HRNet_W48_C_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/HRNet/HRNet_W64_C_train_infer_python.txt b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W64_C_train_infer_python.txt new file mode 100644 index 0000000..c99c5e6 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/HRNet/HRNet_W64_C_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:HRNet_W64_C +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/HRNet/HRNet_W64_C.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/HRNet/HRNet_W64_C.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/HRNet/HRNet_W64_C.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/HRNet_W64_C_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/HarDNet/HarDNet39_ds_train_infer_python.txt b/src/PaddleClas/test_tipc/config/HarDNet/HarDNet39_ds_train_infer_python.txt new file mode 100644 index 0000000..5cda671 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/HarDNet/HarDNet39_ds_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:HarDNet39_ds +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/HarDNet/HarDNet39_ds.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/HarDNet/HarDNet39_ds.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/HarDNet/HarDNet39_ds.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HarDNet39_ds_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/HarDNet/HarDNet68_ds_train_infer_python.txt b/src/PaddleClas/test_tipc/config/HarDNet/HarDNet68_ds_train_infer_python.txt new file mode 100644 index 0000000..bfe601e --- /dev/null +++ b/src/PaddleClas/test_tipc/config/HarDNet/HarDNet68_ds_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:HarDNet68_ds +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/HarDNet/HarDNet68_ds.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/HarDNet/HarDNet68_ds.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/HarDNet/HarDNet68_ds.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HarDNet68_ds_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/HarDNet/HarDNet68_train_infer_python.txt b/src/PaddleClas/test_tipc/config/HarDNet/HarDNet68_train_infer_python.txt new file mode 100644 index 0000000..b61ea63 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/HarDNet/HarDNet68_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:HarDNet68 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/HarDNet/HarDNet68.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/HarDNet/HarDNet68.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/HarDNet/HarDNet68.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HarDNet68_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/HarDNet/HarDNet85_train_infer_python.txt b/src/PaddleClas/test_tipc/config/HarDNet/HarDNet85_train_infer_python.txt new file mode 100644 index 0000000..02237ba --- /dev/null +++ b/src/PaddleClas/test_tipc/config/HarDNet/HarDNet85_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:HarDNet85 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/HarDNet/HarDNet85.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/HarDNet/HarDNet85.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/HarDNet/HarDNet85.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HarDNet85_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Inception/GoogLeNet_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Inception/GoogLeNet_train_infer_python.txt new file mode 100644 index 0000000..ebbb86d --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Inception/GoogLeNet_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:GoogLeNet +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Inception/GoogLeNet.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Inception/GoogLeNet.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Inception/GoogLeNet.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/GoogLeNet_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Inception/InceptionV3_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Inception/InceptionV3_train_infer_python.txt new file mode 100644 index 0000000..6a7960c --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Inception/InceptionV3_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:InceptionV3 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Inception/InceptionV3.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Inception/InceptionV3.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Inception/InceptionV3.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/InceptionV3_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=320 -o PreProcess.transform_ops.1.CropImage.size=299 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Inception/InceptionV4_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Inception/InceptionV4_train_infer_python.txt new file mode 100644 index 0000000..1e1d7fd --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Inception/InceptionV4_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:InceptionV4 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Inception/InceptionV4.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Inception/InceptionV4.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Inception/InceptionV4.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/InceptionV4_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=320 -o PreProcess.transform_ops.1.CropImage.size=299 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/LeViT/LeViT_128S_train_infer_python.txt b/src/PaddleClas/test_tipc/config/LeViT/LeViT_128S_train_infer_python.txt new file mode 100644 index 0000000..772049b --- /dev/null +++ b/src/PaddleClas/test_tipc/config/LeViT/LeViT_128S_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:LeViT_128S +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/LeViT/LeViT_128S.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/LeViT/LeViT_128S.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/LeViT/LeViT_128S.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/LeViT_128S_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/LeViT/LeViT_128_train_infer_python.txt b/src/PaddleClas/test_tipc/config/LeViT/LeViT_128_train_infer_python.txt new file mode 100644 index 0000000..8c8699e --- /dev/null +++ b/src/PaddleClas/test_tipc/config/LeViT/LeViT_128_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:LeViT_128 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/LeViT/LeViT_128.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/LeViT/LeViT_128.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/LeViT/LeViT_128.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/LeViT_128_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/LeViT/LeViT_192_train_infer_python.txt b/src/PaddleClas/test_tipc/config/LeViT/LeViT_192_train_infer_python.txt new file mode 100644 index 0000000..c2ac115 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/LeViT/LeViT_192_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:LeViT_192 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/LeViT/LeViT_192.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/LeViT/LeViT_192.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/LeViT/LeViT_192.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/LeViT_192_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/LeViT/LeViT_256_train_infer_python.txt b/src/PaddleClas/test_tipc/config/LeViT/LeViT_256_train_infer_python.txt new file mode 100644 index 0000000..f58880c --- /dev/null +++ b/src/PaddleClas/test_tipc/config/LeViT/LeViT_256_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:LeViT_256 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/LeViT/LeViT_256.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/LeViT/LeViT_256.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/LeViT/LeViT_256.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/LeViT_256_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/LeViT/LeViT_384_train_infer_python.txt b/src/PaddleClas/test_tipc/config/LeViT/LeViT_384_train_infer_python.txt new file mode 100644 index 0000000..0ae0d40 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/LeViT/LeViT_384_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:LeViT_384 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:2 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/LeViT/LeViT_384.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/LeViT/LeViT_384.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/LeViT/LeViT_384.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/LeViT_384_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=256 -o PreProcess.transform_ops.1.CropImage.size=224 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MixNet/MixNet_L_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MixNet/MixNet_L_train_infer_python.txt new file mode 100644 index 0000000..46fcbc1 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MixNet/MixNet_L_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MixNet_L +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MixNet/MixNet_L.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MixNet/MixNet_L.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MixNet/MixNet_L.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MixNet_L_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MixNet/MixNet_M_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MixNet/MixNet_M_train_infer_python.txt new file mode 100644 index 0000000..87be78a --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MixNet/MixNet_M_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MixNet_M +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MixNet/MixNet_M.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MixNet/MixNet_M.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MixNet/MixNet_M.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MixNet_M_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MixNet/MixNet_S_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MixNet/MixNet_S_train_infer_python.txt new file mode 100644 index 0000000..42e5df7 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MixNet/MixNet_S_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MixNet_S +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MixNet/MixNet_S.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MixNet/MixNet_S.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MixNet/MixNet_S.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MixNet_S_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV1/MobileNetV1_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV1/MobileNetV1_train_infer_python.txt new file mode 100644 index 0000000..65fee15 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV1/MobileNetV1_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MobileNetV1 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV1_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV1/MobileNetV1_x0_25_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV1/MobileNetV1_x0_25_train_infer_python.txt new file mode 100644 index 0000000..a9f63df --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV1/MobileNetV1_x0_25_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MobileNetV1_x0_25 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1_x0_25.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1_x0_25.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1_x0_25.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV1_x0_25_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV1/MobileNetV1_x0_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV1/MobileNetV1_x0_5_train_infer_python.txt new file mode 100644 index 0000000..379cbd6 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV1/MobileNetV1_x0_5_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MobileNetV1_x0_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1_x0_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1_x0_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1_x0_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV1_x0_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV1/MobileNetV1_x0_75_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV1/MobileNetV1_x0_75_train_infer_python.txt new file mode 100644 index 0000000..fef81fa --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV1/MobileNetV1_x0_75_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MobileNetV1_x0_75 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1_x0_75.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1_x0_75.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV1/MobileNetV1_x0_75.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV1_x0_75_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_train_infer_python.txt new file mode 100644 index 0000000..fb0c8a2 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MobileNetV2 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV2_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x0_25_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x0_25_train_infer_python.txt new file mode 100644 index 0000000..9183e01 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x0_25_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MobileNetV2_x0_25 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x0_25.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x0_25.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x0_25.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV2_x0_25_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x0_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x0_5_train_infer_python.txt new file mode 100644 index 0000000..bef4e1d --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x0_5_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MobileNetV2_x0_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x0_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x0_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x0_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV2_x0_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x0_75_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x0_75_train_infer_python.txt new file mode 100644 index 0000000..a788731 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x0_75_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MobileNetV2_x0_75 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x0_75.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x0_75.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x0_75.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV2_x0_75_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x1_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x1_5_train_infer_python.txt new file mode 100644 index 0000000..d5f9bf4 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x1_5_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MobileNetV2_x1_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x1_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x1_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x1_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV2_x1_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x2_0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x2_0_train_infer_python.txt new file mode 100644 index 0000000..f445570 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV2/MobileNetV2_x2_0_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MobileNetV2_x2_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x2_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x2_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV2/MobileNetV2_x2_0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV2_x2_0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x0_35_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x0_35_train_infer_python.txt new file mode 100644 index 0000000..2797a2d --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x0_35_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:MobileNetV3_large_x0_35 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x0_35.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x0_35.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x0_35.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV3_large_x0_35_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x0_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x0_5_train_infer_python.txt new file mode 100644 index 0000000..6f9165c --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x0_5_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:MobileNetV3_large_x0_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x0_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x0_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x0_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV3_large_x0_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x0_75_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x0_75_train_infer_python.txt new file mode 100644 index 0000000..da48671 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x0_75_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:MobileNetV3_large_x0_75 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x0_75.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x0_75.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x0_75.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV3_large_x0_75_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_train_infer_python.txt new file mode 100644 index 0000000..25ecbd5 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MobileNetV3_large_x1_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train|pact_train|fpgm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:tools/train.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_quantization.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +fpgm_train:tools/train.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_prune.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml +quant_export:tools/export_model.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_quantization.yaml +fpgm_export:tools/export_model.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_prune.yaml +distill_export:null +kl_quant:deploy/slim/quant_post_static.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml -o Global.save_inference_dir=./inference +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV3_large_x1_0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt new file mode 100644 index 0000000..c7c956f --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MobileNetV3_large_x1_0 +python:python3.7 +gpu_list:xx.xx.xx.xx,yy.yy.yy.yy;0,1 +-o Global.device:gpu +-o Global.auto_cast:null|amp +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train|pact_train|fpgm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:tools/train.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_quantization.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +fpgm_train:tools/train.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_prune.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml +quant_export:tools/export_model.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_quantization.yaml +fpgm_export:tools/export_model.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_prune.yaml +distill_export:null +kl_quant:deploy/slim/quant_post_static.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml -o Global.save_inference_dir=./inference +export2:null +inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/MobileNetV3_large_x1_0_inference.tar +infer_model:../inference/ +infer_export:null +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt new file mode 100644 index 0000000..f251e9c --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:MobileNetV3_large_x1_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:amp +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train|pact_train|fpgm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:tools/train.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_quantization.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +fpgm_train:tools/train.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_prune.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml +quant_export:tools/export_model.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_quantization.yaml +fpgm_export:tools/export_model.py -c ppcls/configs/slim/MobileNetV3_large_x1_0_prune.yaml +distill_export:null +kl_quant:deploy/slim/quant_post_static.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_0.yaml -o Global.save_inference_dir=./inference +export2:null +inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/MobileNetV3_large_x1_0_inference.tar +infer_model:../inference/ +infer_export:null +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x1_25_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x1_25_train_infer_python.txt new file mode 100644 index 0000000..4b62f54 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_large_x1_25_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:MobileNetV3_large_x1_25 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_25.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_25.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_x1_25.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV3_large_x1_25_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x0_35_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x0_35_train_infer_python.txt new file mode 100644 index 0000000..2e40f89 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x0_35_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:MobileNetV3_small_x0_35 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x0_35.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x0_35.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x0_35.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV3_small_x0_35_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x0_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x0_5_train_infer_python.txt new file mode 100644 index 0000000..e8a2b0e --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x0_5_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:MobileNetV3_small_x0_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x0_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x0_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x0_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV3_small_x0_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x0_75_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x0_75_train_infer_python.txt new file mode 100644 index 0000000..65a8671 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x0_75_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:MobileNetV3_small_x0_75 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x0_75.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x0_75.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x0_75.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV3_small_x0_75_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x1_0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x1_0_train_infer_python.txt new file mode 100644 index 0000000..6d2334b --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x1_0_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:MobileNetV3_small_x1_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x1_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x1_0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV3_small_x1_0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x1_25_train_infer_python.txt b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x1_25_train_infer_python.txt new file mode 100644 index 0000000..6a730b7 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/MobileNetV3/MobileNetV3_small_x1_25_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:MobileNetV3_small_x1_25 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x1_25.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x1_25.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_small_x1_25.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/MobileNetV3_small_x1_25_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/PP-ShiTu/PPShiTu_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/src/PaddleClas/test_tipc/config/PP-ShiTu/PPShiTu_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt new file mode 100644 index 0000000..b86aa9b --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PP-ShiTu/PPShiTu_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt @@ -0,0 +1,19 @@ +===========================cpp_infer_params=========================== +model_name:PPShiTu +cpp_infer_type:shitu +feature_inference_model_dir:./feature_inference/ +det_inference_model_dir:./det_inference +cls_inference_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/general_PPLCNet_x2_5_lite_v1.0_infer.tar +det_inference_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/picodet_PPLCNet_x2_5_mainbody_lite_v1.0_infer.tar +infer_quant:False +inference_cmd:./deploy/cpp_shitu/build/pp_shitu -c inference_drink.yaml +use_gpu:True|False +enable_mkldnn:True|False +cpu_threads:1|6 +batch_size:1 +use_tensorrt:False|True +precision:fp32|fp16 +data_dir:./dataset/drink_dataset_v1.0 +benchmark:True +generate_yaml_cmd:python3 test_tipc/generate_cpp_yaml.py +transform_index_cmd:python3 deploy/cpp_shitu/tools/transform_id_map.py -c inference_drink.yaml diff --git a/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x0_25_train_infer_python.txt b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x0_25_train_infer_python.txt new file mode 100644 index 0000000..66afc24 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x0_25_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:PPLCNet_x0_25 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x0_25.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x0_25.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x0_25.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPLCNet_x0_25_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x0_35_train_infer_python.txt b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x0_35_train_infer_python.txt new file mode 100644 index 0000000..9aa5362 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x0_35_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:PPLCNet_x0_35 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x0_35.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x0_35.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x0_35.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPLCNet_x0_35_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x0_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x0_5_train_infer_python.txt new file mode 100644 index 0000000..277ef81 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x0_5_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:PPLCNet_x0_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x0_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x0_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x0_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPLCNet_x0_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x0_75_train_infer_python.txt b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x0_75_train_infer_python.txt new file mode 100644 index 0000000..14b5ec3 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x0_75_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:PPLCNet_x0_75 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x0_75.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x0_75.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x0_75.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPLCNet_x0_75_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x1_0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x1_0_train_infer_python.txt new file mode 100644 index 0000000..97bec1f --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x1_0_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:PPLCNet_x1_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x1_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x1_0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPLCNet_x1_0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x1_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x1_5_train_infer_python.txt new file mode 100644 index 0000000..6faaddb --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x1_5_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:PPLCNet_x1_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x1_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x1_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x1_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPLCNet_x1_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x2_0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x2_0_train_infer_python.txt new file mode 100644 index 0000000..36145d5 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x2_0_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:PPLCNet_x2_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x2_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x2_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x2_0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPLCNet_x2_0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x2_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x2_5_train_infer_python.txt new file mode 100644 index 0000000..f369e74 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x2_5_train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:PPLCNet_x2_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x2_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x2_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x2_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPLCNet_x2_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x2_5_train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x2_5_train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt new file mode 100644 index 0000000..6637565 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x2_5_train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:PPLCNet_x2_5 +python:python3.7 +gpu_list:xx.xx.xx.xx,yy.yy.yy.yy;0,1 +-o Global.device:gpu +-o Global.auto_cast:null|amp +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x2_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x2_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x2_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPLCNet_x2_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x2_5_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x2_5_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt new file mode 100644 index 0000000..74c6d04 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PPLCNet/PPLCNet_x2_5_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:PPLCNet_x2_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:amp +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x2_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x2_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PPLCNet/PPLCNet_x2_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPLCNet_x2_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null diff --git a/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B0.txt b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B0.txt new file mode 100644 index 0000000..1e0a380 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B0.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:PVT_V2_B0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B0.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=256 -o PreProcess.transform_ops.1.CropImage.size=224 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B1.txt b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B1.txt new file mode 100644 index 0000000..489f8c8 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B1.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:PVT_V2_B1 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B1.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B1.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B1.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B1.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=256 -o PreProcess.transform_ops.1.CropImage.size=224 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B2.txt b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B2.txt new file mode 100644 index 0000000..8d274cd --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B2.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:PVT_V2_B2 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B2.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B2.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B2.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B2.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=256 -o PreProcess.transform_ops.1.CropImage.size=224 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B2_Linear.txt b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B2_Linear.txt new file mode 100644 index 0000000..2fd530c --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B2_Linear.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:PVT_V2_B2_Linear +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B2_Linear.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B2_Linear.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B2_Linear.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B2_Linear.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=256 -o PreProcess.transform_ops.1.CropImage.size=224 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B3.txt b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B3.txt new file mode 100644 index 0000000..f375fcf --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B3.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:PVT_V2_B3 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B3.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B3.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B3.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B3.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=256 -o PreProcess.transform_ops.1.CropImage.size=224 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B4.txt b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B4.txt new file mode 100644 index 0000000..f0c7084 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B4.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:PVT_V2_B4 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B4.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B4.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B4.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B4.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=256 -o PreProcess.transform_ops.1.CropImage.size=224 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B5.txt b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B5.txt new file mode 100644 index 0000000..9383851 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/PVTV2/PVT_V2_B5.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:PVT_V2_B5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/PVTV2/PVT_V2_B5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B5.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=256 -o PreProcess.transform_ops.1.CropImage.size=224 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_1_0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_1_0_train_infer_python.txt new file mode 100644 index 0000000..352ff5e --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_1_0_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ReXNet_1_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_1_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_1_0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ReXNet_1_0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_1_3_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_1_3_train_infer_python.txt new file mode 100644 index 0000000..4c76bad --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_1_3_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ReXNet_1_3 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_1_3.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_1_3.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_1_3.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ReXNet_1_3_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_1_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_1_5_train_infer_python.txt new file mode 100644 index 0000000..b302911 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_1_5_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ReXNet_1_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_1_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_1_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_1_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ReXNet_1_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_2_0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_2_0_train_infer_python.txt new file mode 100644 index 0000000..c52d563 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_2_0_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ReXNet_2_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_2_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_2_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_2_0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ReXNet_2_0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_3_0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_3_0_train_infer_python.txt new file mode 100644 index 0000000..a2047c4 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ReXNet/ReXNet_3_0_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ReXNet_3_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_3_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_3_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ReXNet/ReXNet_3_0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ReXNet_3_0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/RedNet/RedNet101_train_infer_python.txt b/src/PaddleClas/test_tipc/config/RedNet/RedNet101_train_infer_python.txt new file mode 100644 index 0000000..6d7d3b9 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/RedNet/RedNet101_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:RedNet101 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:2 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/RedNet/RedNet101.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/RedNet/RedNet101.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/RedNet/RedNet101.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/RedNet101_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/RedNet/RedNet152_train_infer_python.txt b/src/PaddleClas/test_tipc/config/RedNet/RedNet152_train_infer_python.txt new file mode 100644 index 0000000..82e8189 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/RedNet/RedNet152_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:RedNet152 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:2 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/RedNet/RedNet152.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/RedNet/RedNet152.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/RedNet/RedNet152.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/RedNet152_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/RedNet/RedNet26_train_infer_python.txt b/src/PaddleClas/test_tipc/config/RedNet/RedNet26_train_infer_python.txt new file mode 100644 index 0000000..53e5ce0 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/RedNet/RedNet26_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:RedNet26 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/RedNet/RedNet26.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/RedNet/RedNet26.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/RedNet/RedNet26.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/RedNet26_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/RedNet/RedNet38_train_infer_python.txt b/src/PaddleClas/test_tipc/config/RedNet/RedNet38_train_infer_python.txt new file mode 100644 index 0000000..3ec2471 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/RedNet/RedNet38_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:RedNet38 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/RedNet/RedNet38.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/RedNet/RedNet38.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/RedNet/RedNet38.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/RedNet38_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/RedNet/RedNet50_train_infer_python.txt b/src/PaddleClas/test_tipc/config/RedNet/RedNet50_train_infer_python.txt new file mode 100644 index 0000000..bb36200 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/RedNet/RedNet50_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:RedNet50 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/RedNet/RedNet50.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/RedNet/RedNet50.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/RedNet/RedNet50.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/RedNet50_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Res2Net/Res2Net101_vd_26w_4s_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Res2Net/Res2Net101_vd_26w_4s_train_infer_python.txt new file mode 100644 index 0000000..f5542ad --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Res2Net/Res2Net101_vd_26w_4s_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:Res2Net101_vd_26w_4s +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Res2Net/Res2Net101_vd_26w_4s.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Res2Net/Res2Net101_vd_26w_4s.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Res2Net/Res2Net101_vd_26w_4s.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Res2Net101_vd_26w_4s_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Res2Net/Res2Net200_vd_26w_4s_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Res2Net/Res2Net200_vd_26w_4s_train_infer_python.txt new file mode 100644 index 0000000..40d7f41 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Res2Net/Res2Net200_vd_26w_4s_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:Res2Net200_vd_26w_4s +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Res2Net/Res2Net200_vd_26w_4s.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Res2Net/Res2Net200_vd_26w_4s.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Res2Net/Res2Net200_vd_26w_4s.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Res2Net200_vd_26w_4s_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Res2Net/Res2Net50_14w_8s_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Res2Net/Res2Net50_14w_8s_train_infer_python.txt new file mode 100644 index 0000000..c6300bc --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Res2Net/Res2Net50_14w_8s_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:Res2Net50_14w_8s +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Res2Net/Res2Net50_14w_8s.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Res2Net/Res2Net50_14w_8s.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Res2Net/Res2Net50_14w_8s.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Res2Net50_14w_8s_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Res2Net/Res2Net50_26w_4s_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Res2Net/Res2Net50_26w_4s_train_infer_python.txt new file mode 100644 index 0000000..7491525 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Res2Net/Res2Net50_26w_4s_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:Res2Net50_26w_4s +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Res2Net/Res2Net50_26w_4s.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Res2Net/Res2Net50_26w_4s.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Res2Net/Res2Net50_26w_4s.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Res2Net50_26w_4s_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Res2Net/Res2Net50_vd_26w_4s_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Res2Net/Res2Net50_vd_26w_4s_train_infer_python.txt new file mode 100644 index 0000000..cbdc256 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Res2Net/Res2Net50_vd_26w_4s_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:Res2Net50_vd_26w_4s +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Res2Net/Res2Net50_vd_26w_4s.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Res2Net/Res2Net50_vd_26w_4s.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Res2Net/Res2Net50_vd_26w_4s.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Res2Net50_vd_26w_4s_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeSt/ResNeSt50_fast_1s1x64d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeSt/ResNeSt50_fast_1s1x64d_train_infer_python.txt new file mode 100644 index 0000000..66ce66a --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeSt/ResNeSt50_fast_1s1x64d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeSt50_fast_1s1x64d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeSt/ResNeSt50_fast_1s1x64d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeSt/ResNeSt50_fast_1s1x64d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeSt/ResNeSt50_fast_1s1x64d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeSt50_fast_1s1x64d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeSt/ResNeSt50_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeSt/ResNeSt50_train_infer_python.txt new file mode 100644 index 0000000..2d1bfb2 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeSt/ResNeSt50_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeSt50 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeSt/ResNeSt50.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeSt/ResNeSt50.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeSt/ResNeSt50.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeSt50_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt101_32x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt101_32x4d_train_infer_python.txt new file mode 100644 index 0000000..eb21af6 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt101_32x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeXt101_32x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_32x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_32x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_32x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeXt101_32x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt101_64x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt101_64x4d_train_infer_python.txt new file mode 100644 index 0000000..8e4ac81 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt101_64x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeXt101_64x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_64x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_64x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_64x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeXt101_64x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt101_vd_32x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt101_vd_32x4d_train_infer_python.txt new file mode 100644 index 0000000..cf9211f --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt101_vd_32x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeXt101_vd_32x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_vd_32x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_vd_32x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_vd_32x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeXt101_vd_32x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt101_vd_64x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt101_vd_64x4d_train_infer_python.txt new file mode 100644 index 0000000..eae4d0e --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt101_vd_64x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeXt101_vd_64x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_vd_64x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_vd_64x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_vd_64x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeXt101_vd_64x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt152_32x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt152_32x4d_train_infer_python.txt new file mode 100644 index 0000000..eb21af6 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt152_32x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeXt101_32x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_32x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_32x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt101_32x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeXt101_32x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt152_64x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt152_64x4d_train_infer_python.txt new file mode 100644 index 0000000..c8a85f6 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt152_64x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeXt152_64x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt152_64x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt152_64x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt152_64x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeXt152_64x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt152_vd_32x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt152_vd_32x4d_train_infer_python.txt new file mode 100644 index 0000000..4abaa87 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt152_vd_32x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeXt152_vd_32x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt152_vd_32x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt152_vd_32x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt152_vd_32x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeXt152_vd_32x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt152_vd_64x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt152_vd_64x4d_train_infer_python.txt new file mode 100644 index 0000000..8d8a4ea --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt152_vd_64x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeXt152_vd_64x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt152_vd_64x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt152_vd_64x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt152_vd_64x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeXt152_vd_64x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt50_32x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt50_32x4d_train_infer_python.txt new file mode 100644 index 0000000..4cb942f --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt50_32x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeXt50_32x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt50_32x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt50_32x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt50_32x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeXt50_32x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt50_64x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt50_64x4d_train_infer_python.txt new file mode 100644 index 0000000..0cad348 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt50_64x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeXt50_64x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt50_64x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt50_64x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt50_64x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeXt50_64x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt50_vd_32x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt50_vd_32x4d_train_infer_python.txt new file mode 100644 index 0000000..fc74560 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt50_vd_32x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeXt50_vd_32x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt50_vd_32x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt50_vd_32x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt50_vd_32x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeXt50_vd_32x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt50_vd_64x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt50_vd_64x4d_train_infer_python.txt new file mode 100644 index 0000000..b2817db --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNeXt/ResNeXt50_vd_64x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNeXt50_vd_64x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt50_vd_64x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt50_vd_64x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNeXt/ResNeXt50_vd_64x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeXt50_vd_64x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet101_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet101_train_infer_python.txt new file mode 100644 index 0000000..f10760d --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet101_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNet101 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet101.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet101.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet101.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ResNet101_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet101_vd_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet101_vd_train_infer_python.txt new file mode 100644 index 0000000..7027d30 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet101_vd_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNet101_vd +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet101_vd.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet101_vd.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet101_vd.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ResNet101_vd_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet152_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet152_train_infer_python.txt new file mode 100644 index 0000000..1d4cc80 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet152_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNet152 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet152.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet152.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet152.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ResNet152_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet152_vd_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet152_vd_train_infer_python.txt new file mode 100644 index 0000000..4091328 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet152_vd_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNet152_vd +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet152_vd.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet152_vd.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet152_vd.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ResNet152_vd_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet18_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet18_train_infer_python.txt new file mode 100644 index 0000000..06d5504 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet18_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNet18 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet18.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet18.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet18.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ResNet18_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet18_vd_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet18_vd_train_infer_python.txt new file mode 100644 index 0000000..d3d2bcf --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet18_vd_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNet18_vd +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet18_vd.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet18_vd.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet18_vd.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ResNet18_vd_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet200_vd_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet200_vd_train_infer_python.txt new file mode 100644 index 0000000..e742e87 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet200_vd_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNet200_vd +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet200_vd.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet200_vd.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet200_vd.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ResNet200_vd_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet34_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet34_train_infer_python.txt new file mode 100644 index 0000000..4a520b5 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet34_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNet34 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet34.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet34.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet34.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ResNet34_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet34_vd_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet34_vd_train_infer_python.txt new file mode 100644 index 0000000..b956c83 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet34_vd_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNet34_vd +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet34_vd.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet34_vd.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet34_vd.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ResNet34_vd_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet50_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_train_infer_python.txt new file mode 100644 index 0000000..6775f95 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNet50 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet50.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet50.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet50.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ResNet50_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt new file mode 100644 index 0000000..51c73f1 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt @@ -0,0 +1,18 @@ +===========================cpp_infer_params=========================== +model_name:ResNet50_vd +cpp_infer_type:cls +cls_inference_model_dir:./cls_inference/ +det_inference_model_dir: +cls_inference_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/ResNet50_vd_inference.tar +det_inference_url: +infer_quant:False +inference_cmd:./deploy/cpp/build/clas_system -c inference_cls.yaml +use_gpu:True|False +enable_mkldnn:True|False +cpu_threads:1|6 +batch_size:1 +use_tensorrt:False|True +precision:fp32|fp16 +image_dir:./dataset/ILSVRC2012/val +benchmark:True +generate_yaml_cmd:python3 test_tipc/generate_cpp_yaml.py diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt new file mode 100644 index 0000000..163bb48 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt @@ -0,0 +1,14 @@ +===========================paddle2onnx_params=========================== +model_name:ResNet50_vd +python:python3.7 +2onnx: paddle2onnx +--model_dir:./deploy/models/ResNet50_vd_infer/ +--model_filename:inference.pdmodel +--params_filename:inference.pdiparams +--save_file:./deploy/models/ResNet50_vd_infer/inference.onnx +--opset_version:10 +--enable_onnx_checker:True +inference: python/predict_cls.py -c configs/inference_cls.yaml +Global.use_onnx:True +Global.inference_model_dir:models/ResNet50_vd_infer/ +Global.use_gpu:False diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt new file mode 100644 index 0000000..d16ecd3 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNet50_vd +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train|pact_train|fpgm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:tools/train.py -c ppcls/configs/slim/ResNet50_vd_quantization.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +fpgm_train:tools/train.py -c ppcls/configs/slim/ResNet50_vd_prune.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml +quant_export:tools/export_model.py -c ppcls/configs/slim/ResNet50_vd_quantization.yaml +fpgm_export:tools/export_model.py -c ppcls/configs/slim/ResNet50_vd_prune.yaml +distill_export:null +kl_quant:deploy/slim/quant_post_static.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml -o Global.save_inference_dir=./inference +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/ResNet50_vd_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt new file mode 100644 index 0000000..2cb6915 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNet50_vd +python:python3.7 +gpu_list:xx.xx.xx.xx,yy.yy.yy.yy;0,1 +-o Global.device:gpu +-o Global.auto_cast:null|amp +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train|pact_train|fpgm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:tools/train.py -c ppcls/configs/slim/ResNet50_vd_quantization.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +fpgm_train:tools/train.py -c ppcls/configs/slim/ResNet50_vd_prune.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml +quant_export:tools/export_model.py -c ppcls/configs/slim/ResNet50_vd_quantization.yaml +fpgm_export:tools/export_model.py -c ppcls/configs/slim/ResNet50_vd_prune.yaml +distill_export:null +kl_quant:deploy/slim/quant_post_static.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml -o Global.save_inference_dir=./inference +export2:null +inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/ResNet50_vd_inference.tar +infer_model:../inference/ +infer_export:null +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt new file mode 100644 index 0000000..22c0f8d --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ResNet50_vd +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:amp +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train|pact_train|fpgm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:tools/train.py -c ppcls/configs/slim/ResNet50_vd_quantization.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +fpgm_train:tools/train.py -c ppcls/configs/slim/ResNet50_vd_prune.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml +quant_export:tools/export_model.py -c ppcls/configs/slim/ResNet50_vd_quantization.yaml +fpgm_export:tools/export_model.py -c ppcls/configs/slim/ResNet50_vd_prune.yaml +distill_export:null +kl_quant:deploy/slim/quant_post_static.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml -o Global.save_inference_dir=./inference +export2:null +inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/whole_chain/ResNet50_vd_inference.tar +infer_model:../inference/ +infer_export:null +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_train_linux_gpu_use_dali.txt b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_train_linux_gpu_use_dali.txt new file mode 100644 index 0000000..9d4bf7f --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ResNet/ResNet50_vd_train_linux_gpu_use_dali.txt @@ -0,0 +1,22 @@ +===========================train_params=========================== +model_name:ResNet50_vd +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null|amp +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.use_dali=True +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## diff --git a/src/PaddleClas/test_tipc/config/SENet/SENet154_vd_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SENet/SENet154_vd_train_infer_python.txt new file mode 100644 index 0000000..29d2954 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SENet/SENet154_vd_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SENet154_vd +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SENet/SENet154_vd.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SENet/SENet154_vd.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SENet/SENet154_vd.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SENet154_vd_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SENet/SE_ResNeXt101_32x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SENet/SE_ResNeXt101_32x4d_train_infer_python.txt new file mode 100644 index 0000000..023dceb --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SENet/SE_ResNeXt101_32x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SE_ResNeXt101_32x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SENet/SE_ResNeXt101_32x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SENet/SE_ResNeXt101_32x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SENet/SE_ResNeXt101_32x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SE_ResNeXt101_32x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SENet/SE_ResNeXt50_32x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SENet/SE_ResNeXt50_32x4d_train_infer_python.txt new file mode 100644 index 0000000..e6c6db7 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SENet/SE_ResNeXt50_32x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SE_ResNeXt50_32x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SENet/SE_ResNeXt50_32x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SENet/SE_ResNeXt50_32x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SENet/SE_ResNeXt50_32x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SE_ResNeXt50_32x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SENet/SE_ResNeXt50_vd_32x4d_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SENet/SE_ResNeXt50_vd_32x4d_train_infer_python.txt new file mode 100644 index 0000000..c2704f9 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SENet/SE_ResNeXt50_vd_32x4d_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SE_ResNeXt50_vd_32x4d +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SENet/SE_ResNeXt50_vd_32x4d.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SENet/SE_ResNeXt50_vd_32x4d.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SENet/SE_ResNeXt50_vd_32x4d.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SE_ResNeXt50_vd_32x4d_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SENet/SE_ResNet18_vd_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SENet/SE_ResNet18_vd_train_infer_python.txt new file mode 100644 index 0000000..095b1b9 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SENet/SE_ResNet18_vd_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SE_ResNet18_vd +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SENet/SE_ResNet18_vd.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SENet/SE_ResNet18_vd.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SENet/SE_ResNet18_vd.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SE_ResNet18_vd_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SENet/SE_ResNet34_vd_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SENet/SE_ResNet34_vd_train_infer_python.txt new file mode 100644 index 0000000..260bc63 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SENet/SE_ResNet34_vd_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SE_ResNet34_vd +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SENet/SE_ResNet34_vd.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SENet/SE_ResNet34_vd.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SENet/SE_ResNet34_vd.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SE_ResNet34_vd_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SENet/SE_ResNet50_vd_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SENet/SE_ResNet50_vd_train_infer_python.txt new file mode 100644 index 0000000..b486f3c --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SENet/SE_ResNet50_vd_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SE_ResNet50_vd +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SENet/SE_ResNet50_vd.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SENet/SE_ResNet50_vd.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SENet/SE_ResNet50_vd.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SE_ResNet50_vd_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_swish_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_swish_train_infer_python.txt new file mode 100644 index 0000000..616e269 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_swish_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ShuffleNetV2_swish +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_swish.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_swish.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_swish.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ShuffleNetV2_swish_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x0_25_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x0_25_train_infer_python.txt new file mode 100644 index 0000000..df20812 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x0_25_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ShuffleNetV2_x0_25 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x0_25.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x0_25.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x0_25.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ShuffleNetV2_x0_25_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x0_33_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x0_33_train_infer_python.txt new file mode 100644 index 0000000..91df1ac --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x0_33_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ShuffleNetV2_x0_33 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x0_33.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x0_33.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x0_33.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ShuffleNetV2_x0_33_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x0_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x0_5_train_infer_python.txt new file mode 100644 index 0000000..e0ee753 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x0_5_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ShuffleNetV2_x0_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x0_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x0_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x0_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ShuffleNetV2_x0_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x1_0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x1_0_train_infer_python.txt new file mode 100644 index 0000000..a0f354c --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x1_0_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ShuffleNetV2_x1_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x1_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x1_0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ShuffleNetV2_x1_0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x1_5_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x1_5_train_infer_python.txt new file mode 100644 index 0000000..f9ab9c1 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x1_5_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ShuffleNetV2_x1_5 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x1_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x1_5.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x1_5.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ShuffleNetV2_x1_5_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x2_0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x2_0_train_infer_python.txt new file mode 100644 index 0000000..eea768a --- /dev/null +++ b/src/PaddleClas/test_tipc/config/ShuffleNet/ShuffleNetV2_x2_0_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ShuffleNetV2_x2_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x2_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x2_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/ShuffleNet/ShuffleNetV2_x2_0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ShuffleNetV2_x2_0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SqueezeNet/SqueezeNet1_0_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SqueezeNet/SqueezeNet1_0_train_infer_python.txt new file mode 100644 index 0000000..49c59a9 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SqueezeNet/SqueezeNet1_0_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SqueezeNet1_0 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SqueezeNet/SqueezeNet1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SqueezeNet/SqueezeNet1_0.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SqueezeNet/SqueezeNet1_0.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SqueezeNet1_0_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SqueezeNet/SqueezeNet1_1_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SqueezeNet/SqueezeNet1_1_train_infer_python.txt new file mode 100644 index 0000000..1b957af --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SqueezeNet/SqueezeNet1_1_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SqueezeNet1_1 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SqueezeNet/SqueezeNet1_1.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SqueezeNet/SqueezeNet1_1.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SqueezeNet/SqueezeNet1_1.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SqueezeNet1_1_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_base_patch4_window12_384_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_base_patch4_window12_384_train_infer_python.txt new file mode 100644 index 0000000..e7161c8 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_base_patch4_window12_384_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SwinTransformer_base_patch4_window12_384 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_base_patch4_window12_384.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_base_patch4_window12_384.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_base_patch4_window12_384.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SwinTransformer_base_patch4_window12_384_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=384 -o PreProcess.transform_ops.1.CropImage.size=384 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_base_patch4_window7_224_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_base_patch4_window7_224_train_infer_python.txt new file mode 100644 index 0000000..2307086 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_base_patch4_window7_224_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SwinTransformer_base_patch4_window7_224 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_base_patch4_window7_224.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_base_patch4_window7_224.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_base_patch4_window7_224.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SwinTransformer_base_patch4_window7_224_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_large_patch4_window12_384_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_large_patch4_window12_384_train_infer_python.txt new file mode 100644 index 0000000..f1a1873 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_large_patch4_window12_384_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SwinTransformer_large_patch4_window12_384 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:2 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_large_patch4_window12_384.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_large_patch4_window12_384.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_large_patch4_window12_384.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SwinTransformer_large_patch4_window12_384_22kto1k_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=384 -o PreProcess.transform_ops.1.CropImage.size=384 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_large_patch4_window7_224_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_large_patch4_window7_224_train_infer_python.txt new file mode 100644 index 0000000..359899e --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_large_patch4_window7_224_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SwinTransformer_large_patch4_window7_224 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_large_patch4_window7_224.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_large_patch4_window7_224.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_large_patch4_window7_224.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SwinTransformer_large_patch4_window7_224_22kto1k_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_small_patch4_window7_224_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_small_patch4_window7_224_train_infer_python.txt new file mode 100644 index 0000000..7f9edb8 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_small_patch4_window7_224_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SwinTransformer_small_patch4_window7_224 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_small_patch4_window7_224.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_small_patch4_window7_224.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_small_patch4_window7_224.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SwinTransformer_small_patch4_window7_224_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_tiny_patch4_window7_224_train_infer_python.txt b/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_tiny_patch4_window7_224_train_infer_python.txt new file mode 100644 index 0000000..80b76ed --- /dev/null +++ b/src/PaddleClas/test_tipc/config/SwinTransformer/SwinTransformer_tiny_patch4_window7_224_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:SwinTransformer_tiny_patch4_window7_224 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_tiny_patch4_window7_224.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_tiny_patch4_window7_224.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SwinTransformer/SwinTransformer_tiny_patch4_window7_224.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SwinTransformer_tiny_patch4_window7_224_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/TNT/TNT_small_train_infer_python.txt b/src/PaddleClas/test_tipc/config/TNT/TNT_small_train_infer_python.txt new file mode 100644 index 0000000..20d4264 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/TNT/TNT_small_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:TNT_small +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/TNT/TNT_small.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/TNT/TNT_small.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/TNT/TNT_small.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/TNT_small_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Twins/alt_gvt_base_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Twins/alt_gvt_base_train_infer_python.txt new file mode 100644 index 0000000..a08a732 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Twins/alt_gvt_base_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:alt_gvt_base +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Twins/alt_gvt_base.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Twins/alt_gvt_base.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Twins/alt_gvt_base.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/alt_gvt_base_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Twins/alt_gvt_large_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Twins/alt_gvt_large_train_infer_python.txt new file mode 100644 index 0000000..d75f8a1 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Twins/alt_gvt_large_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:alt_gvt_large +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:2 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Twins/alt_gvt_large.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Twins/alt_gvt_large.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Twins/alt_gvt_large.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/alt_gvt_large_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Twins/alt_gvt_small_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Twins/alt_gvt_small_train_infer_python.txt new file mode 100644 index 0000000..d0686e5 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Twins/alt_gvt_small_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:alt_gvt_small +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Twins/alt_gvt_small.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Twins/alt_gvt_small.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Twins/alt_gvt_small.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/alt_gvt_small_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Twins/pcpvt_base_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Twins/pcpvt_base_train_infer_python.txt new file mode 100644 index 0000000..76486b8 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Twins/pcpvt_base_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:pcpvt_base +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Twins/pcpvt_base.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Twins/pcpvt_base.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Twins/pcpvt_base.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/pcpvt_base_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Twins/pcpvt_large_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Twins/pcpvt_large_train_infer_python.txt new file mode 100644 index 0000000..928c0b3 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Twins/pcpvt_large_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:pcpvt_large +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:2 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Twins/pcpvt_large.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Twins/pcpvt_large.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Twins/pcpvt_large.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/pcpvt_large_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Twins/pcpvt_small_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Twins/pcpvt_small_train_infer_python.txt new file mode 100644 index 0000000..9ce13df --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Twins/pcpvt_small_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:pcpvt_small +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Twins/pcpvt_small.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Twins/pcpvt_small.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Twins/pcpvt_small.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/pcpvt_small_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/VGG/VGG11_train_infer_python.txt b/src/PaddleClas/test_tipc/config/VGG/VGG11_train_infer_python.txt new file mode 100644 index 0000000..4d5f7b1 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/VGG/VGG11_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:VGG11 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/VGG/VGG11.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/VGG/VGG11.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/VGG/VGG11.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/VGG11_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/VGG/VGG13_train_infer_python.txt b/src/PaddleClas/test_tipc/config/VGG/VGG13_train_infer_python.txt new file mode 100644 index 0000000..737a56b --- /dev/null +++ b/src/PaddleClas/test_tipc/config/VGG/VGG13_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:VGG13 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/VGG/VGG13.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/VGG/VGG13.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/VGG/VGG13.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/VGG13_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/VGG/VGG16_train_infer_python.txt b/src/PaddleClas/test_tipc/config/VGG/VGG16_train_infer_python.txt new file mode 100644 index 0000000..b8bf46f --- /dev/null +++ b/src/PaddleClas/test_tipc/config/VGG/VGG16_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:VGG16 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/VGG/VGG16.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/VGG/VGG16.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/VGG/VGG16.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/VGG16_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/VGG/VGG19_train_infer_python.txt b/src/PaddleClas/test_tipc/config/VGG/VGG19_train_infer_python.txt new file mode 100644 index 0000000..3f5a8f3 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/VGG/VGG19_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:VGG19 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/VGG/VGG19.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/VGG/VGG19.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/VGG/VGG19.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/VGG19_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_base_patch16_224_train_infer_python.txt b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_base_patch16_224_train_infer_python.txt new file mode 100644 index 0000000..d9f6e2f --- /dev/null +++ b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_base_patch16_224_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ViT_base_patch16_224 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_base_patch16_224.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_base_patch16_224.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_base_patch16_224.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ViT_base_patch16_224_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_base_patch16_384_train_infer_python.txt b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_base_patch16_384_train_infer_python.txt new file mode 100644 index 0000000..ed88b51 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_base_patch16_384_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ViT_base_patch16_384 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_base_patch16_384.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_base_patch16_384.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_base_patch16_384.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ViT_base_patch16_384_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=384 -o PreProcess.transform_ops.1.CropImage.size=384 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_base_patch32_384_train_infer_python.txt b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_base_patch32_384_train_infer_python.txt new file mode 100644 index 0000000..9c3abcd --- /dev/null +++ b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_base_patch32_384_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ViT_base_patch32_384 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_base_patch32_384.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_base_patch32_384.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_base_patch32_384.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ViT_base_patch32_384_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=384 -o PreProcess.transform_ops.1.CropImage.size=384 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_large_patch16_224_train_infer_python.txt b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_large_patch16_224_train_infer_python.txt new file mode 100644 index 0000000..ec77af6 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_large_patch16_224_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ViT_large_patch16_224 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:2 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_large_patch16_224.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_large_patch16_224.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_large_patch16_224.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ViT_large_patch16_224_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_large_patch16_384_train_infer_python.txt b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_large_patch16_384_train_infer_python.txt new file mode 100644 index 0000000..e05c6df --- /dev/null +++ b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_large_patch16_384_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ViT_large_patch16_384 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:2 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_large_patch16_384.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_large_patch16_384.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_large_patch16_384.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ViT_large_patch16_384_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=384 -o PreProcess.transform_ops.1.CropImage.size=384 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_large_patch32_384_train_infer_python.txt b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_large_patch32_384_train_infer_python.txt new file mode 100644 index 0000000..43b313f --- /dev/null +++ b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_large_patch32_384_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ViT_large_patch32_384 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:2 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_large_patch32_384.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_large_patch32_384.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_large_patch32_384.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ViT_large_patch32_384_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=384 -o PreProcess.transform_ops.1.CropImage.size=384 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_small_patch16_224_train_infer_python.txt b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_small_patch16_224_train_infer_python.txt new file mode 100644 index 0000000..6fc2cd0 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/VisionTransformer/ViT_small_patch16_224_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:ViT_small_patch16_224 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_small_patch16_224.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_small_patch16_224.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/VisionTransformer/ViT_small_patch16_224.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ViT_small_patch16_224_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Xception/Xception41_deeplab_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Xception/Xception41_deeplab_train_infer_python.txt new file mode 100644 index 0000000..b9c1621 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Xception/Xception41_deeplab_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:Xception41_deeplab +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Xception/Xception41_deeplab.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Xception/Xception41_deeplab.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Xception/Xception41_deeplab.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Xception41_deeplab_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=320 -o PreProcess.transform_ops.1.CropImage.size=299 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Xception/Xception41_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Xception/Xception41_train_infer_python.txt new file mode 100644 index 0000000..7d7fbf1 --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Xception/Xception41_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:Xception41 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Xception/Xception41.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Xception/Xception41.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Xception/Xception41.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Xception41_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=320 -o PreProcess.transform_ops.1.CropImage.size=299 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Xception/Xception65_deeplab_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Xception/Xception65_deeplab_train_infer_python.txt new file mode 100644 index 0000000..adf12cb --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Xception/Xception65_deeplab_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:Xception65_deeplab +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Xception/Xception65_deeplab.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Xception/Xception65_deeplab.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Xception/Xception65_deeplab.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Xception65_deeplab_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=320 -o PreProcess.transform_ops.1.CropImage.size=299 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Xception/Xception65_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Xception/Xception65_train_infer_python.txt new file mode 100644 index 0000000..463e20d --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Xception/Xception65_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:Xception65 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Xception/Xception65.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Xception/Xception65.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Xception/Xception65.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Xception65_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=320 -o PreProcess.transform_ops.1.CropImage.size=299 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/config/Xception/Xception71_train_infer_python.txt b/src/PaddleClas/test_tipc/config/Xception/Xception71_train_infer_python.txt new file mode 100644 index 0000000..52ea37d --- /dev/null +++ b/src/PaddleClas/test_tipc/config/Xception/Xception71_train_infer_python.txt @@ -0,0 +1,52 @@ +===========================train_params=========================== +model_name:Xception71 +python:python3.7 +gpu_list:0|0,1 +-o Global.device:gpu +-o Global.auto_cast:null +-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120 +-o Global.output_dir:./output/ +-o DataLoader.Train.sampler.batch_size:8 +-o Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./dataset/ILSVRC2012/val +null:null +## +trainer:norm_train +norm_train:tools/train.py -c ppcls/configs/ImageNet/Xception/Xception71.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False +pact_train:null +fpgm_train:null +distill_train:null +null:null +null:null +## +===========================eval_params=========================== +eval:tools/eval.py -c ppcls/configs/ImageNet/Xception/Xception71.yaml +null:null +## +===========================infer_params========================== +-o Global.save_inference_dir:./inference +-o Global.pretrained_model: +norm_export:tools/export_model.py -c ppcls/configs/ImageNet/Xception/Xception71.yaml +quant_export:null +fpgm_export:null +distill_export:null +kl_quant:null +export2:null +pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Xception71_pretrained.pdparams +infer_model:../inference/ +infer_export:True +infer_quant:Fasle +inference:python/predict_cls.py -c configs/inference_cls.yaml -o PreProcess.transform_ops.0.ResizeImage.resize_short=320 -o PreProcess.transform_ops.1.CropImage.size=299 +-o Global.use_gpu:True|False +-o Global.enable_mkldnn:True|False +-o Global.cpu_num_threads:1|6 +-o Global.batch_size:1|16 +-o Global.use_tensorrt:True|False +-o Global.use_fp16:True|False +-o Global.inference_model_dir:../inference +-o Global.infer_imgs:../dataset/ILSVRC2012/val +-o Global.save_log_path:null +-o Global.benchmark:True +null:null +null:null diff --git a/src/PaddleClas/test_tipc/docs/compare_cpp_right.png b/src/PaddleClas/test_tipc/docs/compare_cpp_right.png new file mode 100644 index 0000000..f9d0ba8 Binary files /dev/null and b/src/PaddleClas/test_tipc/docs/compare_cpp_right.png differ diff --git a/src/PaddleClas/test_tipc/docs/compare_cpp_wrong.png b/src/PaddleClas/test_tipc/docs/compare_cpp_wrong.png new file mode 100644 index 0000000..621d446 Binary files /dev/null and b/src/PaddleClas/test_tipc/docs/compare_cpp_wrong.png differ diff --git a/src/PaddleClas/test_tipc/docs/compare_right.png b/src/PaddleClas/test_tipc/docs/compare_right.png new file mode 100644 index 0000000..3d74ef1 Binary files /dev/null and b/src/PaddleClas/test_tipc/docs/compare_right.png differ diff --git a/src/PaddleClas/test_tipc/docs/compare_wrong.png b/src/PaddleClas/test_tipc/docs/compare_wrong.png new file mode 100644 index 0000000..26ad576 Binary files /dev/null and b/src/PaddleClas/test_tipc/docs/compare_wrong.png differ diff --git a/src/PaddleClas/test_tipc/docs/guide.png b/src/PaddleClas/test_tipc/docs/guide.png new file mode 100644 index 0000000..319ac81 Binary files /dev/null and b/src/PaddleClas/test_tipc/docs/guide.png differ diff --git a/src/PaddleClas/test_tipc/docs/install.md b/src/PaddleClas/test_tipc/docs/install.md new file mode 100644 index 0000000..35e2866 --- /dev/null +++ b/src/PaddleClas/test_tipc/docs/install.md @@ -0,0 +1,121 @@ +## 1. 环境准备 + +本教程适用于test_tipc目录下基础功能测试的运行环境搭建。 + +推荐环境： +- CUDA 10.1/10.2 +- CUDNN 7.6/cudnn8.1 +- TensorRT 6.1.0.5 / 7.1 / 7.2 + +环境配置可以选择docker镜像安装，或者在本地环境Python搭建环境。推荐使用docker镜像安装，避免不必要的环境配置。 + +## 2. Docker 镜像安装 + +推荐docker镜像安装，按照如下命令创建镜像，当前目录映射到镜像中的`/paddle`目录下 +``` +nvidia-docker run --name paddle -it -v $PWD:/paddle paddlepaddle/paddle:latest-dev-cuda10.1-cudnn7-gcc82 /bin/bash +cd /paddle + +# 安装带TRT的paddle +pip3.7 install https://paddle-wheel.bj.bcebos.com/with-trt/2.1.3/linux-gpu-cuda10.1-cudnn7-mkl-gcc8.2-trt6-avx/paddlepaddle_gpu-2.1.3.post101-cp37-cp37m-linux_x86_64.whl +``` + +## 3 Python 环境构建 + +非docker环境下，环境配置比较灵活，推荐环境组合配置： +- CUDA10.1 + CUDNN7.6 + TensorRT 6 +- CUDA10.2 + CUDNN8.1 + TensorRT 7 +- CUDA11.1 + CUDNN8.1 + TensorRT 7 + +下面以 CUDA10.2 + CUDNN8.1 + TensorRT 7 配置为例，介绍环境配置的流程。 + +### 3.1 安装CUDNN + +如果当前环境满足CUDNN版本的要求，可以跳过此步骤。 + +以CUDNN8.1 安装安装为例，安装步骤如下，首先下载CUDNN，从[Nvidia官网](https://developer.nvidia.com/rdp/cudnn-archive)下载CUDNN8.1版本，下载符合当前系统版本的三个deb文件，分别是： +- cuDNN Runtime Library ，如：libcudnn8_8.1.0.77-1+cuda10.2_amd64.deb +- cuDNN Developer Library ，如：libcudnn8-dev_8.1.0.77-1+cuda10.2_amd64.deb +- cuDNN Code Samples，如：libcudnn8-samples_8.1.0.77-1+cuda10.2_amd64.deb + +deb安装可以参考[官方文档](https://docs.nvidia.com/deeplearning/cudnn/install-guide/index.html#installlinux-deb)，安装方式如下 +``` +# x.x.x表示下载的版本号 +# $HOME为工作目录 +sudo dpkg -i libcudnn8_x.x.x-1+cudax.x_arm64.deb +sudo dpkg -i libcudnn8-dev_8.x.x.x-1+cudax.x_arm64.deb +sudo dpkg -i libcudnn8-samples_8.x.x.x-1+cudax.x_arm64.deb + +# 验证是否正确安装 +cp -r /usr/src/cudnn_samples_v8/ $HOME +cd $HOME/cudnn_samples_v8/mnistCUDNN + +# 编译 +make clean && make +./mnistCUDNN +``` +如果运行mnistCUDNN完后提示运行成功，则表示安装成功。如果运行后出现freeimage相关的报错，需要按照提示安装freeimage库: +``` +sudo apt-get install libfreeimage-dev +sudo apt-get install libfreeimage +``` + +### 3.2 安装TensorRT + +首先，从[Nvidia官网TensorRT板块](https://developer.nvidia.com/tensorrt-getting-started)下载TensorRT，这里选择7.1.3.4版本的TensorRT，注意选择适合自己系统版本和CUDA版本的TensorRT，另外建议下载TAR package的安装包。 + +以Ubuntu16.04+CUDA10.2为例，下载并解压后可以参考[官方文档](https://docs.nvidia.com/deeplearning/tensorrt/archives/tensorrt-713/install-guide/index.html#installing-tar)的安装步骤，按照如下步骤安装: +``` +# 以下安装命令中 '${version}' 为下载的TensorRT版本，如7.1.3.4 +# 设置环境变量， 为解压后的TensorRT的lib目录 +export LD_LIBRARY_PATH=$LD_LIBRARY_PATH: + +# 安装TensorRT +cd TensorRT-${version}/python +pip3.7 install tensorrt-*-cp3x-none-linux_x86_64.whl + +# 安装graphsurgeon +cd TensorRT-${version}/graphsurgeon +``` + + +### 3.3 安装PaddlePaddle + +下载支持TensorRT版本的Paddle安装包，注意安装包的TensorRT版本需要与本地TensorRT一致，下载[链接](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html#python) +选择下载 linux-cuda10.2-trt7-gcc8.2 Python3.7版本的Paddle： +``` +# 从下载链接中可以看到是paddle2.1.1-cuda10.2-cudnn8.1版本 +wget https://paddle-wheel.bj.bcebos.com/with-trt/2.1.1-gpu-cuda10.2-cudnn8.1-mkl-gcc8.2/paddlepaddle_gpu-2.1.1-cp37-cp37m-linux_x86_64.whl +pip3.7 install -U paddlepaddle_gpu-2.1.1-cp37-cp37m-linux_x86_64.whl +``` + +## 4. 安装PaddleClas依赖 +``` +# 安装AutoLog +git clone https://github.com/LDOUBLEV/AutoLog +cd AutoLog +pip3.7 install -r requirements.txt +python3.7 setup.py bdist_wheel +pip3.7 install ./dist/auto_log-1.0.0-py3-none-any.whl + +# 下载Clas代码 +cd ../ +git clone https://github.com/PaddlePaddle/PaddleClas + +``` + +安装PaddleClas依赖： +``` +cd PaddleClas +pip3.7 install -r requirements.txt +``` + +## FAQ : +Q. You are using Paddle compiled with TensorRT, but TensorRT dynamic library is not found. Ignore this if TensorRT is not needed. + +A. 问题一般是当前安装paddle版本带TRT，但是本地环境找不到TensorRT的预测库，需要下载TensorRT库，解压后设置环境变量LD_LIBRARY_PATH; +如： +``` +export LD_LIBRARY_PATH=/usr/local/python3.7.0/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/paddle/package/TensorRT-6.0.1.5/lib +``` +或者问题是下载的TensorRT版本和当前paddle中编译的TRT版本不匹配，需要下载版本相符的TensorRT重新安装。 diff --git a/src/PaddleClas/test_tipc/docs/test.png b/src/PaddleClas/test_tipc/docs/test.png new file mode 100644 index 0000000..f99f23d Binary files /dev/null and b/src/PaddleClas/test_tipc/docs/test.png differ diff --git a/src/PaddleClas/test_tipc/docs/test_inference_cpp.md b/src/PaddleClas/test_tipc/docs/test_inference_cpp.md new file mode 100644 index 0000000..eabf877 --- /dev/null +++ b/src/PaddleClas/test_tipc/docs/test_inference_cpp.md @@ -0,0 +1,86 @@ +# C++预测功能测试 + +C++预测功能测试的主程序为`test_inference_cpp.sh`，可以测试基于C++预测库的模型推理功能。 + +## 1. 测试结论汇总 + +基于训练是否使用量化，进行本测试的模型可以分为`正常模型`和`量化模型`，这两类模型对应的C++预测功能汇总如下： + +| 模型类型 |device | batchsize | tensorrt | mkldnn | cpu多线程 | +| ---- | ---- | ---- | :----: | :----: | :----: | +| 正常模型 | GPU | 1/6 | fp32/fp16 | - | - | +| 正常模型 | CPU | 1/6 | - | fp32 | 支持 | +| 量化模型 | GPU | 1/6 | int8 | - | - | +| 量化模型 | CPU | 1/6 | - | int8 | 支持 | + +## 2. 测试流程 +运行环境配置请参考[文档](./install.md)的内容配置TIPC的运行环境。 + +### 2.1 功能测试 +先运行`prepare.sh`准备数据和模型，然后运行`test_inference_cpp.sh`进行测试，最终在```test_tipc/output```目录下生成`cpp_infer_*.log`后缀的日志文件。 + +```shell +bash test_tipc/prepare.sh test_tipc/config/ResNet/ResNet50_vd_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt cpp_infer + +# 用法1: +bash test_tipc/test_inference_cpp.sh test_tipc/config/ResNet/ResNet50_vd_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt +# 用法2: 指定GPU卡预测，第三个传入参数为GPU卡号 +bash test_tipc/test_inference_cpp.sh test_tipc/config/ResNet/ResNet50_vd_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt 1 +``` + +运行预测指令后，在`test_tipc/output`文件夹下自动会保存运行日志，包括以下文件： + +```shell +test_tipc/output/ +|- results_cpp.log # 运行指令状态的日志 +|- cls_cpp_infer_cpu_usemkldnn_False_threads_1_precision_fp32_batchsize_1.log # CPU上不开启Mkldnn，线程数设置为1，测试batch_size=1条件下的预测运行日志 +|- cls_cpp_infer_cpu_usemkldnn_False_threads_6_precision_fp32_batchsize_1.log # CPU上不开启Mkldnn，线程数设置为6，测试batch_size=1条件下的预测运行日志 +|- cls_cpp_infer_gpu_usetrt_False_precision_fp32_batchsize_1.log # GPU上不开启TensorRT，测试batch_size=1的fp32精度预测日志 +|- cls_cpp_infer_gpu_usetrt_True_precision_fp16_batchsize_1.log # GPU上开启TensorRT，测试batch_size=1的fp16精度预测日志 +...... +``` +其中results_cpp.log中包含了每条指令的运行状态，如果运行成功会输出： + +``` +Run successfully with command - ./deploy/cpp/build/clas_system -c inference_cls.yaml 2>&1|tee test_tipc/output/cls_cpp_infer_gpu_usetrt_False_precision_fp32_batchsize_1.log +...... +``` +如果运行失败，会输出： +``` +Run failed with command - ./deploy/cpp/build/clas_system -c inference_cls.yaml 2>&1|tee test_tipc/output/cls_cpp_infer_gpu_usetrt_False_precision_fp32_batchsize_1.log +...... +``` +可以很方便的根据results_cpp.log中的内容判定哪一个指令运行错误。 + + +### 2.2 精度测试 + +使用compare_results.py脚本比较模型预测的结果是否符合预期，主要步骤包括： +- 提取日志中的预测坐标； +- 从本地文件中提取保存好的坐标结果； +- 比较上述两个结果是否符合精度预期，误差大于设置阈值时会报错。 + +#### 使用方式 +运行命令： +```shell +python3.7 test_tipc/compare_results.py --gt_file=./test_tipc/results/cls_cpp_*.txt --log_file=./test_tipc/output/cls_cpp_*.log --atol=1e-3 --rtol=1e-3 +``` + +参数介绍： +- gt_file： 指向事先保存好的预测结果路径，支持*.txt 结尾，会自动索引*.txt格式的文件，文件默认保存在test_tipc/result/ 文件夹下 +- log_file: 指向运行test_tipc/test_inference_cpp.sh 脚本的infer模式保存的预测日志，预测日志中打印的有预测结果，比如：文本框，预测文本，类别等等，同样支持cpp_infer_*.log格式传入 +- atol: 设置的绝对误差 +- rtol: 设置的相对误差 + +#### 运行结果 + +正常运行效果如下图： + + +出现不一致结果时的运行输出： + + + +## 3. 更多教程 + +本文档为功能测试用，更详细的c++预测使用教程请参考：[服务器端C++预测](../../docs/zh_CN/inference_deployment/) diff --git a/src/PaddleClas/test_tipc/docs/test_train_inference_python.md b/src/PaddleClas/test_tipc/docs/test_train_inference_python.md new file mode 100644 index 0000000..ef25e14 --- /dev/null +++ b/src/PaddleClas/test_tipc/docs/test_train_inference_python.md @@ -0,0 +1,154 @@ +# Linux端基础训练预测功能测试 + +Linux端基础训练预测功能测试的主程序为`test_train_inference_python.sh`，可以测试基于Python的模型训练、评估、推理等基本功能，包括裁剪、量化、蒸馏。 + +- Mac端基础训练预测功能测试参考[链接](./mac_test_train_inference_python.md) +- Windows端基础训练预测功能测试参考[链接](./win_test_train_inference_python.md) + +## 1. 测试结论汇总 + +- 训练相关： + +| 算法名称 | 模型名称 | 单机单卡 | 单机多卡 | 多机多卡 | 模型压缩（单机多卡） | +| :---- | :---- | :---- | :---- | :---- | :---- | +| MobileNetV3 | MobileNetV3_large_x1_0 | 正常训练
混合精度 | 正常训练
混合精度 | 正常训练
混合精度 | 正常训练：FPGM裁剪、PACT量化
离线量化（无需训练） | +| ResNet50 | ResNet50_vd | 正常训练
混合精度 | 正常训练
混合精度 | 正常训练
混合精度 | 正常训练：FPGM裁剪、PACT量化
离线量化（无需训练） | + + +- 预测相关：基于训练是否使用量化，可以将训练产出的模型可以分为`正常模型`和`量化模型`，这两类模型对应的预测功能汇总如下， + +| 模型类型 |device | batchsize | tensorrt | mkldnn | cpu多线程 | +| ---- | ---- | ---- | :----: | :----: | :----: | +| 正常模型 | GPU | 1/6 | fp32/fp16 | - | - | +| 正常模型 | CPU | 1/6 | - | fp32/fp16 | 支持 | +| 量化模型 | GPU | 1/6 | int8 | - | - | +| 量化模型 | CPU | 1/6 | - | int8 | 支持 | + + +## 2. 测试流程 + +运行环境配置请参考[文档](./install.md)的内容配置TIPC的运行环境。 + +### 2.1 安装依赖 +- 安装PaddlePaddle >= 2.2 +- 安装PaddleClas依赖 + ``` + pip3 install -r ../requirements.txt + ``` +- 安装autolog（规范化日志输出工具） + ``` + git clone https://github.com/LDOUBLEV/AutoLog + cd AutoLog + pip3 install -r requirements.txt + python3 setup.py bdist_wheel + pip3 install ./dist/auto_log-1.0.0-py3-none-any.whl + cd ../ + ``` +- 安装PaddleSlim (可选) + ``` + # 如果要测试量化、裁剪等功能，需要安装PaddleSlim + pip3 install paddleslim + ``` + + +### 2.2 功能测试 +先运行`prepare.sh`准备数据和模型，然后运行`test_train_inference_python.sh`进行测试，最终在```test_tipc/output```目录下生成`python_infer_*.log`格式的日志文件。 + +`test_train_inference_python.sh`包含5种运行模式，每种模式的运行数据不同，分别用于测试速度和精度，分别是： + +- 模式1：lite_train_lite_infer，使用少量数据训练，用于快速验证训练到预测的走通流程，不验证精度和速度； +```shell +bash test_tipc/prepare.sh ./test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt 'lite_train_lite_infer' +bash test_tipc/test_train_inference_python.sh ./test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt 'lite_train_lite_infer' +``` + +- 模式2：lite_train_whole_infer，使用少量数据训练，一定量数据预测，用于验证训练后的模型执行预测，预测速度是否合理； +```shell +bash test_tipc/prepare.sh ./test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt 'lite_train_whole_infer' +bash test_tipc/test_train_inference_python.sh ./test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt 'lite_train_whole_infer' +``` + +- 模式3：whole_infer，不训练，全量数据预测，走通开源模型评估、动转静，检查inference model预测时间和精度; +```shell +bash test_tipc/prepare.sh ./test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt 'whole_infer' +# 用法1: +bash test_tipc/test_train_inference_python.sh ./test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt 'whole_infer' +# 用法2: 指定GPU卡预测，第三个传入参数为GPU卡号 +bash test_tipc/test_train_inference_python.sh ./test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt 'whole_infer' '1' +``` + +- 模式4：whole_train_whole_infer，CE： 全量数据训练，全量数据预测，验证模型训练精度，预测精度，预测速度； +```shell +bash test_tipc/prepare.sh ./test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt 'whole_train_whole_infer' +bash test_tipc/test_train_inference_python.sh ./test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt 'whole_train_whole_infer' +``` + +- 模式5: klquant_whole_infer，测试离线量化； + +```shell +bash test_tipc/prepare.sh ./test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt 'klquant_whole_infer' +bash test_tipc/test_train_inference_python.sh ./test_tipc/config/ResNet/ResNet50_vd_train_infer_python.txt 'klquant_whole_infer' +``` + + + +运行相应指令后，在`test_tipc/output`文件夹下自动会保存运行日志。如'lite_train_lite_infer'模式下，会运行训练+inference的链条，因此，在`test_tipc/output`文件夹有以下文件： + +``` +test_tipc/output/ +|- results_python.log # 运行指令状态的日志 +|- norm_train_gpus_0_autocast_null/ # GPU 0号卡上正常训练的训练日志和模型保存文件夹 +|- pact_train_gpus_0_autocast_null/ # GPU 0号卡上量化训练的训练日志和模型保存文件夹 +...... +|- python_infer_cpu_usemkldnn_True_threads_1_batchsize_1.log # CPU上开启Mkldnn线程数设置为1，测试batch_size=1条件下的预测运行日志 +|- python_infer_gpu_usetrt_True_precision_fp16_batchsize_1.log # GPU上开启TensorRT，测试batch_size=1的半精度预测日志 +...... +``` + +其中`results_python.log`中包含了每条指令的运行状态，如果运行成功会输出： +``` +Run successfully with command - python3.7 tools/train.py -c tests/configs/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained Global.use_gpu=True Global.save_model_dir=./tests/output/norm_train_gpus_0_autocast_null Global.epoch_num=1 Train.loader.batch_size_per_card=2 ! +Run successfully with command - python3.7 tools/export_model.py -c tests/configs/det_mv3_db.yml -o Global.pretrained_model=./tests/output/norm_train_gpus_0_autocast_null/latest Global.save_inference_dir=./tests/output/norm_train_gpus_0_autocast_null! +...... +``` +如果运行失败，会输出： +``` +Run failed with command - python3.7 tools/train.py -c tests/configs/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained Global.use_gpu=True Global.save_model_dir=./tests/output/norm_train_gpus_0_autocast_null Global.epoch_num=1 Train.loader.batch_size_per_card=2 ! +Run failed with command - python3.7 tools/export_model.py -c tests/configs/det_mv3_db.yml -o Global.pretrained_model=./tests/output/norm_train_gpus_0_autocast_null/latest Global.save_inference_dir=./tests/output/norm_train_gpus_0_autocast_null! +...... +``` +可以很方便的根据`results_python.log`中的内容判定哪一个指令运行错误。 + + +### 2.3 精度测试 + +使用compare_results.py脚本比较模型预测的结果是否符合预期，主要步骤包括： +- 提取日志中的预测坐标； +- 从本地文件中提取保存好的坐标结果； +- 比较上述两个结果是否符合精度预期，误差大于设置阈值时会报错。 + +#### 使用方式 +运行命令： +```shell +python3.7 test_tipc/compare_results.py --gt_file=./test_tipc/results/python_*.txt --log_file=./test_tipc/output/python_*.log --atol=1e-3 --rtol=1e-3 +``` + +参数介绍： +- gt_file： 指向事先保存好的预测结果路径，支持*.txt 结尾，会自动索引*.txt格式的文件，文件默认保存在test_tipc/result/ 文件夹下 +- log_file: 指向运行test_tipc/test_train_inference_python.sh 脚本的infer模式保存的预测日志，预测日志中打印的有预测结果，比如：文本框，预测文本，类别等等，同样支持python_infer_*.log格式传入 +- atol: 设置的绝对误差 +- rtol: 设置的相对误差 + +#### 运行结果 + +正常运行效果如下图： + + +出现不一致结果时的运行输出： + + + +## 3. 更多教程 +本文档为功能测试用，更丰富的训练预测使用教程请参考： +[模型训练](../../docs/zh_CN/models_training) +[基于Python预测引擎推理](../../docs/zh_CN/inference_deployment/python_deploy.md) diff --git a/src/PaddleClas/test_tipc/generate_cpp_yaml.py b/src/PaddleClas/test_tipc/generate_cpp_yaml.py new file mode 100644 index 0000000..2e541de --- /dev/null +++ b/src/PaddleClas/test_tipc/generate_cpp_yaml.py @@ -0,0 +1,80 @@ +import os +import yaml +import argparse + + +def str2bool(v): + if v.lower() == 'true': + return True + else: + return False + + +def parse_args(): + parser = argparse.ArgumentParser() + parser.add_argument('--type', required=True, choices=["cls", "shitu"]) + parser.add_argument('--batch_size', type=int, default=1) + parser.add_argument('--mkldnn', type=str2bool, default=True) + parser.add_argument('--gpu', type=str2bool, default=False) + parser.add_argument('--cpu_thread', type=int, default=1) + parser.add_argument('--tensorrt', type=str2bool, default=False) + parser.add_argument('--precision', type=str, choices=["fp32", "fp16"]) + parser.add_argument('--benchmark', type=str2bool, default=True) + parser.add_argument('--gpu_id', type=int, default=0) + parser.add_argument( + '--cls_yaml_path', + type=str, + default="deploy/configs/inference_cls.yaml") + parser.add_argument( + '--shitu_yaml_path', + type=str, + default="deploy/configs/inference_drink.yaml") + parser.add_argument('--data_dir', type=str, required=True) + parser.add_argument('--save_path', type=str, default='./') + parser.add_argument('--cls_model_dir', type=str) + parser.add_argument('--det_model_dir', type=str) + args = parser.parse_args() + return args + + +def main(): + args = parse_args() + if args.type == "cls": + save_path = os.path.join(args.save_path, + os.path.basename(args.cls_yaml_path)) + fd = open(args.cls_yaml_path) + else: + save_path = os.path.join(args.save_path, + os.path.basename(args.shitu_yaml_path)) + fd = open(args.shitu_yaml_path) + config = yaml.load(fd, yaml.FullLoader) + fd.close() + + config["Global"]["batch_size"] = args.batch_size + config["Global"]["use_gpu"] = args.gpu + config["Global"]["enable_mkldnn"] = args.mkldnn + config["Global"]["benchmark"] = args.benchmark + config["Global"]["use_tensorrt"] = args.tensorrt + config["Global"]["use_fp16"] = True if args.precision == "fp16" else False + config["Global"]["gpu_id"] = args.gpu_id + if args.type == "cls": + config["Global"]["infer_imgs"] = args.data_dir + assert args.cls_model_dir + config["Global"]["inference_model_dir"] = args.cls_model_dir + else: + config["Global"]["infer_imgs"] = os.path.join(args.data_dir, + "test_images") + config["IndexProcess"]["index_dir"] = os.path.join(args.data_dir, + "index") + assert args.cls_model_dir + assert args.det_model_dir + config["Global"]["det_inference_model_dir"] = args.det_model_dir + config["Global"]["rec_inference_model_dir"] = args.cls_model_dir + + with open(save_path, 'w') as fd: + yaml.dump(config, fd) + print("Generate new yaml done") + + +if __name__ == "__main__": + main() diff --git a/src/PaddleClas/test_tipc/prepare.sh b/src/PaddleClas/test_tipc/prepare.sh new file mode 100644 index 0000000..acb2eb0 --- /dev/null +++ b/src/PaddleClas/test_tipc/prepare.sh @@ -0,0 +1,184 @@ +#!/bin/bash +FILENAME=$1 + +# MODE be one of ['lite_train_lite_infer' 'lite_train_whole_infer' 'whole_train_whole_infer', +# 'whole_infer', 'klquant_whole_infer', +# 'cpp_infer', 'serving_infer', 'lite_infer'] + +MODE=$2 + +dataline=$(cat ${FILENAME}) +# parser params +IFS=$'\n' +lines=(${dataline}) + +function func_parser_key(){ + strs=$1 + IFS=":" + array=(${strs}) + tmp=${array[0]} + echo ${tmp} +} + +function func_parser_value(){ + strs=$1 + IFS=":" + array=(${strs}) + if [ ${#array[*]} = 2 ]; then + echo ${array[1]} + else + IFS="|" + tmp="${array[1]}:${array[2]}" + echo ${tmp} + fi +} + +function func_get_url_file_name(){ + strs=$1 + IFS="/" + array=(${strs}) + tmp=${array[${#array[@]}-1]} + echo ${tmp} +} + +model_name=$(func_parser_value "${lines[1]}") + +if [ ${MODE} = "cpp_infer" ];then + if [[ $FILENAME == *infer_cpp_linux_gpu_cpu.txt ]];then + cpp_type=$(func_parser_value "${lines[2]}") + cls_inference_model_dir=$(func_parser_value "${lines[3]}") + det_inference_model_dir=$(func_parser_value "${lines[4]}") + cls_inference_url=$(func_parser_value "${lines[5]}") + det_inference_url=$(func_parser_value "${lines[6]}") + + if [[ $cpp_type == "cls" ]];then + eval "wget -nc $cls_inference_url" + tar xf "${model_name}_inference.tar" + eval "mv inference $cls_inference_model_dir" + cd dataset + rm -rf ILSVRC2012 + wget -nc https://paddle-imagenet-models-name.bj.bcebos.com/data/whole_chain/whole_chain_infer.tar + tar xf whole_chain_infer.tar + ln -s whole_chain_infer ILSVRC2012 + cd .. + elif [[ $cpp_type == "shitu" ]];then + eval "wget -nc $cls_inference_url" + tar_name=$(func_get_url_file_name "$cls_inference_url") + model_dir=${tar_name%.*} + eval "tar xf ${tar_name}" + eval "mv ${model_dir} ${cls_inference_model_dir}" + + eval "wget -nc $det_inference_url" + tar_name=$(func_get_url_file_name "$det_inference_url") + model_dir=${tar_name%.*} + eval "tar xf ${tar_name}" + eval "mv ${model_dir} ${det_inference_model_dir}" + cd dataset + wget -nc https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/drink_dataset_v1.0.tar + tar -xf drink_dataset_v1.0.tar + else + echo "Wrong cpp type in config file in line 3. only support cls, shitu" + fi + exit 0 + else + echo "use wrong config file" + exit 1 + fi +fi + +model_name=$(func_parser_value "${lines[1]}") +model_url_value=$(func_parser_value "${lines[35]}") +model_url_key=$(func_parser_key "${lines[35]}") + +if [[ $FILENAME == *GeneralRecognition* ]];then + cd dataset + rm -rf Aliproduct + rm -rf train_reg_all_data.txt + rm -rf demo_train + wget -nc https://paddle-imagenet-models-name.bj.bcebos.com/data/whole_chain/tipc_shitu_demo_data.tar + tar -xf tipc_shitu_demo_data.tar + ln -s tipc_shitu_demo_data Aliproduct + ln -s tipc_shitu_demo_data/demo_train.txt train_reg_all_data.txt + ln -s tipc_shitu_demo_data/demo_train demo_train + cd tipc_shitu_demo_data + ln -s demo_test.txt val_list.txt + cd ../../ + eval "wget -nc $model_url_value" + mv general_PPLCNet_x2_5_pretrained_v1.0.pdparams GeneralRecognition_PPLCNet_x2_5_pretrained.pdparams + exit 0 +fi + +if [[ $FILENAME == *use_dali* ]];then + python_name=$(func_parser_value "${lines[2]}") + ${python_name} -m pip install --extra-index-url https://developer.download.nvidia.com/compute/redist/nightly --upgrade nvidia-dali-nightly-cuda102 +fi + +if [ ${MODE} = "lite_train_lite_infer" ] || [ ${MODE} = "lite_train_whole_infer" ];then + # pretrain lite train data + cd dataset + rm -rf ILSVRC2012 + wget -nc https://paddle-imagenet-models-name.bj.bcebos.com/data/whole_chain/whole_chain_little_train.tar + tar xf whole_chain_little_train.tar + ln -s whole_chain_little_train ILSVRC2012 + cd ILSVRC2012 + mv train.txt train_list.txt + mv val.txt val_list.txt + cp -r train/* val/ + cd ../../ +elif [ ${MODE} = "whole_infer" ] || [ ${MODE} = "klquant_whole_infer" ];then + # download data + cd dataset + rm -rf ILSVRC2012 + wget -nc https://paddle-imagenet-models-name.bj.bcebos.com/data/whole_chain/whole_chain_infer.tar + tar xf whole_chain_infer.tar + ln -s whole_chain_infer ILSVRC2012 + cd ILSVRC2012 + mv val.txt val_list.txt + ln -s val_list.txt train_list.txt + cd ../../ + # download inference or pretrained model + eval "wget -nc $model_url_value" + if [[ $model_url_key == *inference* ]]; then + rm -rf inference + tar xf "${model_name}_inference.tar" + fi + if [[ $model_name == "SwinTransformer_large_patch4_window7_224" || $model_name == "SwinTransformer_large_patch4_window12_384" ]];then + cmd="mv ${model_name}_22kto1k_pretrained.pdparams ${model_name}_pretrained.pdparams" + eval $cmd + fi + +elif [ ${MODE} = "whole_train_whole_infer" ];then + cd dataset + rm -rf ILSVRC2012 + wget -nc https://paddle-imagenet-models-name.bj.bcebos.com/data/whole_chain/whole_chain_CIFAR100.tar + tar xf whole_chain_CIFAR100.tar + ln -s whole_chain_CIFAR100 ILSVRC2012 + cd ILSVRC2012 + mv train.txt train_list.txt + mv test.txt val_list.txt + cd ../../ +fi + +if [ ${MODE} = "serving_infer" ];then + # prepare serving env + python_name=$(func_parser_value "${lines[2]}") + ${python_name} -m pip install install paddle-serving-server-gpu==0.6.1.post101 + ${python_name} -m pip install paddle_serving_client==0.6.1 + ${python_name} -m pip install paddle-serving-app==0.6.1 + unset http_proxy + unset https_proxy + cd ./deploy/paddleserving + wget -nc https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/ResNet50_vd_infer.tar && tar xf ResNet50_vd_infer.tar +fi + +if [ ${MODE} = "paddle2onnx_infer" ];then + # prepare paddle2onnx env + python_name=$(func_parser_value "${lines[2]}") + ${python_name} -m pip install install paddle2onnx + ${python_name} -m pip install onnxruntime + + # wget model + cd deploy && mkdir models && cd models + wget -nc https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/ResNet50_vd_infer.tar && tar xf ResNet50_vd_infer.tar + cd ../../ +fi diff --git a/src/PaddleClas/test_tipc/prepare_lite_cpp.sh b/src/PaddleClas/test_tipc/prepare_lite_cpp.sh new file mode 100644 index 0000000..b129322 --- /dev/null +++ b/src/PaddleClas/test_tipc/prepare_lite_cpp.sh @@ -0,0 +1,93 @@ +#!/bin/bash +source ./test_tipc/common_func.sh +FILENAME=$1 +dataline=$(cat ${FILENAME}) +# parser params +IFS=$'\n' +lines=(${dataline}) +IFS=$'\n' + +inference_cmd=$(func_parser_value "${lines[1]}") +DEVICE=$(func_parser_value "${lines[2]}") +det_lite_model_list=$(func_parser_value "${lines[3]}") +rec_lite_model_list=$(func_parser_value "${lines[4]}") +cls_lite_model_list=$(func_parser_value "${lines[5]}") + +if [[ $inference_cmd =~ "det" ]];then + lite_model_list=${det_lite_model_list} +elif [[ $inference_cmd =~ "rec" ]];then + lite_model_list=(${rec_lite_model_list[*]} ${cls_lite_model_list[*]}) +elif [[ $inference_cmd =~ "system" ]];then + lite_model_list=(${det_lite_model_list[*]} ${rec_lite_model_list[*]} ${cls_lite_model_list[*]}) +else + echo "inference_cmd is wrong, please check." + exit 1 +fi + +if [ ${DEVICE} = "ARM_CPU" ];then + valid_targets="arm" + paddlelite_url="https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10-rc/inference_lite_lib.android.armv8.gcc.c++_shared.with_extra.with_cv.tar.gz" + end_index="66" +elif [ ${DEVICE} = "ARM_GPU_OPENCL" ];then + valid_targets="opencl" + paddlelite_url="https://github.com/PaddlePaddle/Paddle-Lite/releases/download/v2.10-rc/inference_lite_lib.armv8.clang.with_exception.with_extra.with_cv.opencl.tar.gz" + end_index="71" +else + echo "DEVICE only suport ARM_CPU, ARM_GPU_OPENCL." + exit 2 +fi + +# prepare lite .nb model +pip install paddlelite==2.10-rc +current_dir=${PWD} +IFS="|" +model_path=./inference_models + +for model in ${lite_model_list[*]}; do + if [[ $model =~ "PP-OCRv2" ]];then + inference_model_url=https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/${model}.tar + elif [[ $model =~ "v2.0" ]];then + inference_model_url=https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/${model}.tar + else + echo "Model is wrong, please check." + exit 3 + fi + inference_model=${inference_model_url##*/} + wget -nc -P ${model_path} ${inference_model_url} + cd ${model_path} && tar -xf ${inference_model} && cd ../ + model_dir=${model_path}/${inference_model%.*} + model_file=${model_dir}/inference.pdmodel + param_file=${model_dir}/inference.pdiparams + paddle_lite_opt --model_dir=${model_dir} --model_file=${model_file} --param_file=${param_file} --valid_targets=${valid_targets} --optimize_out=${model_dir}_opt +done + +# prepare test data +data_url=https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015_lite.tar +model_path=./inference_models +inference_model=${inference_model_url##*/} +data_file=${data_url##*/} +wget -nc -P ./inference_models ${inference_model_url} +wget -nc -P ./test_data ${data_url} +cd ./inference_models && tar -xf ${inference_model} && cd ../ +cd ./test_data && tar -xf ${data_file} && rm ${data_file} && cd ../ + +# prepare lite env +paddlelite_zipfile=$(echo $paddlelite_url | awk -F "/" '{print $NF}') +paddlelite_file=${paddlelite_zipfile:0:${end_index}} +wget ${paddlelite_url} && tar -xf ${paddlelite_zipfile} +mkdir -p ${paddlelite_file}/demo/cxx/ocr/test_lite +cp -r ${model_path}/*_opt.nb test_data ${paddlelite_file}/demo/cxx/ocr/test_lite +cp ppocr/utils/ppocr_keys_v1.txt deploy/lite/config.txt ${paddlelite_file}/demo/cxx/ocr/test_lite +cp -r ./deploy/lite/* ${paddlelite_file}/demo/cxx/ocr/ +cp ${paddlelite_file}/cxx/lib/libpaddle_light_api_shared.so ${paddlelite_file}/demo/cxx/ocr/test_lite +cp ${FILENAME} test_tipc/test_lite_arm_cpp.sh test_tipc/common_func.sh ${paddlelite_file}/demo/cxx/ocr/test_lite +cd ${paddlelite_file}/demo/cxx/ocr/ +git clone https://github.com/cuicheng01/AutoLog.git + +# make +make -j +sleep 1 +make -j +cp ocr_db_crnn test_lite && cp test_lite/libpaddle_light_api_shared.so test_lite/libc++_shared.so +tar -cf test_lite.tar ./test_lite && cp test_lite.tar ${current_dir} && cd ${current_dir} +rm -rf ${paddlelite_file}* && rm -rf ${model_path} diff --git a/src/PaddleClas/test_tipc/test_inference_cpp.sh b/src/PaddleClas/test_tipc/test_inference_cpp.sh new file mode 100644 index 0000000..129e439 --- /dev/null +++ b/src/PaddleClas/test_tipc/test_inference_cpp.sh @@ -0,0 +1,303 @@ +#!/bin/bash +source test_tipc/common_func.sh + +FILENAME=$1 +GPUID=$2 +if [[ ! $GPUID ]];then + GPUID=0 +fi +dataline=$(awk 'NR==1, NR==16{print}' $FILENAME) + +# parser params +IFS=$'\n' +lines=(${dataline}) + +# parser cpp inference model +model_name=$(func_parser_value "${lines[1]}") +cpp_infer_type=$(func_parser_value "${lines[2]}") +cpp_infer_model_dir=$(func_parser_value "${lines[3]}") +cpp_det_infer_model_dir=$(func_parser_value "${lines[4]}") +cpp_infer_is_quant=$(func_parser_value "${lines[7]}") +# parser cpp inference +inference_cmd=$(func_parser_value "${lines[8]}") +cpp_use_gpu_list=$(func_parser_value "${lines[9]}") +cpp_use_mkldnn_list=$(func_parser_value "${lines[10]}") +cpp_cpu_threads_list=$(func_parser_value "${lines[11]}") +cpp_batch_size_list=$(func_parser_value "${lines[12]}") +cpp_use_trt_list=$(func_parser_value "${lines[13]}") +cpp_precision_list=$(func_parser_value "${lines[14]}") +cpp_image_dir_value=$(func_parser_value "${lines[15]}") +cpp_benchmark_value=$(func_parser_value "${lines[16]}") +generate_yaml_cmd=$(func_parser_value "${lines[17]}") +transform_index_cmd=$(func_parser_value "${lines[18]}") + +LOG_PATH="./test_tipc/output" +mkdir -p ${LOG_PATH} +status_log="${LOG_PATH}/results_cpp.log" +# generate_yaml_cmd="python3 test_tipc/generate_cpp_yaml.py" + +function func_shitu_cpp_inference(){ + IFS='|' + _script=$1 + _model_dir=$2 + _log_path=$3 + _img_dir=$4 + _flag_quant=$5 + # inference + + for use_gpu in ${cpp_use_gpu_list[*]}; do + if [ ${use_gpu} = "False" ] || [ ${use_gpu} = "cpu" ]; then + for use_mkldnn in ${cpp_use_mkldnn_list[*]}; do + if [ ${use_mkldnn} = "False" ] && [ ${_flag_quant} = "True" ]; then + continue + fi + for threads in ${cpp_cpu_threads_list[*]}; do + for batch_size in ${cpp_batch_size_list[*]}; do + precision="fp32" + if [ ${use_mkldnn} = "False" ] && [ ${_flag_quant} = "True" ]; then + precison="int8" + fi + _save_log_path="${_log_path}/shitu_cpp_infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_precision_${precision}_batchsize_${batch_size}.log" + + command="${generate_yaml_cmd} --type shitu --batch_size ${batch_size} --mkldnn ${use_mkldnn} --gpu ${use_gpu} --cpu_thread ${threads} --tensorrt False --precision ${precision} --data_dir ${_img_dir} --benchmark True --cls_model_dir ${cpp_infer_model_dir} --det_model_dir ${cpp_det_infer_model_dir} --gpu_id ${GPUID}" + eval $command + eval $transform_index_cmd + command="${_script} 2>&1|tee ${_save_log_path}" + eval $command + last_status=${PIPESTATUS[0]} + status_check $last_status "${command}" "${status_log}" + done + done + done + elif [ ${use_gpu} = "True" ] || [ ${use_gpu} = "gpu" ]; then + for use_trt in ${cpp_use_trt_list[*]}; do + for precision in ${cpp_precision_list[*]}; do + if [[ ${_flag_quant} = "False" ]] && [[ ${precision} =~ "int8" ]]; then + continue + fi + if [[ ${precision} =~ "fp16" || ${precision} =~ "int8" ]] && [ ${use_trt} = "False" ]; then + continue + fi + if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [ ${_flag_quant} = "True" ]; then + continue + fi + for batch_size in ${cpp_batch_size_list[*]}; do + _save_log_path="${_log_path}/shitu_cpp_infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}.log" + command="${generate_yaml_cmd} --type shitu --batch_size ${batch_size} --mkldnn False --gpu ${use_gpu} --cpu_thread 1 --tensorrt ${use_trt} --precision ${precision} --data_dir ${_img_dir} --benchmark True --cls_model_dir ${cpp_infer_model_dir} --det_model_dir ${cpp_det_infer_model_dir} --gpu_id ${GPUID}" + eval $command + eval $transform_index_cmd + command="${_script} 2>&1|tee ${_save_log_path}" + eval $command + last_status=${PIPESTATUS[0]} + status_check $last_status "${_script}" "${status_log}" + done + done + done + else + echo "Does not support hardware other than CPU and GPU Currently!" + fi + done +} + +function func_cls_cpp_inference(){ + IFS='|' + _script=$1 + _model_dir=$2 + _log_path=$3 + _img_dir=$4 + _flag_quant=$5 + # inference + + for use_gpu in ${cpp_use_gpu_list[*]}; do + if [ ${use_gpu} = "False" ] || [ ${use_gpu} = "cpu" ]; then + for use_mkldnn in ${cpp_use_mkldnn_list[*]}; do + if [ ${use_mkldnn} = "False" ] && [ ${_flag_quant} = "True" ]; then + continue + fi + for threads in ${cpp_cpu_threads_list[*]}; do + for batch_size in ${cpp_batch_size_list[*]}; do + precision="fp32" + if [ ${use_mkldnn} = "False" ] && [ ${_flag_quant} = "True" ]; then + precison="int8" + fi + _save_log_path="${_log_path}/cls_cpp_infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_precision_${precision}_batchsize_${batch_size}.log" + + command="${generate_yaml_cmd} --type cls --batch_size ${batch_size} --mkldnn ${use_mkldnn} --gpu ${use_gpu} --cpu_thread ${threads} --tensorrt False --precision ${precision} --data_dir ${_img_dir} --benchmark True --cls_model_dir ${cpp_infer_model_dir} --gpu_id ${GPUID}" + eval $command + command1="${_script} 2>&1|tee ${_save_log_path}" + eval ${command1} + last_status=${PIPESTATUS[0]} + status_check $last_status "${command1}" "${status_log}" + done + done + done + elif [ ${use_gpu} = "True" ] || [ ${use_gpu} = "gpu" ]; then + for use_trt in ${cpp_use_trt_list[*]}; do + for precision in ${cpp_precision_list[*]}; do + if [[ ${_flag_quant} = "False" ]] && [[ ${precision} =~ "int8" ]]; then + continue + fi + if [[ ${precision} =~ "fp16" || ${precision} =~ "int8" ]] && [ ${use_trt} = "False" ]; then + continue + fi + if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [ ${_flag_quant} = "True" ]; then + continue + fi + for batch_size in ${cpp_batch_size_list[*]}; do + _save_log_path="${_log_path}/cls_cpp_infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}.log" + command="${generate_yaml_cmd} --type cls --batch_size ${batch_size} --mkldnn False --gpu ${use_gpu} --cpu_thread 1 --tensorrt ${use_trt} --precision ${precision} --data_dir ${_img_dir} --benchmark True --cls_model_dir ${cpp_infer_model_dir} --gpu_id ${GPUID}" + eval $command + command="${_script} 2>&1|tee ${_save_log_path}" + eval $command + last_status=${PIPESTATUS[0]} + status_check $last_status "${command}" "${status_log}" + done + done + done + else + echo "Does not support hardware other than CPU and GPU Currently!" + fi + done +} + + +if [[ $cpp_infer_type == "cls" ]]; then + cd deploy/cpp +elif [[ $cpp_infer_type == "shitu" ]]; then + cd deploy/cpp_shitu +else + echo "Only support cls and shitu" + exit 0 +fi + +if [[ $cpp_infer_type == "shitu" ]]; then + echo "################### update cmake ###################" + wget -nc https://github.com/Kitware/CMake/releases/download/v3.22.0/cmake-3.22.0.tar.gz + tar xf cmake-3.22.0.tar.gz + cd ./cmake-3.22.0 + export root_path=$PWD + export install_path=${root_path}/cmake + eval "./bootstrap --prefix=${install_path}" + make -j + make install + export PATH=${install_path}/bin:$PATH + cd .. + echo "################### update cmake done ###################" + + echo "################### build faiss ###################" + apt-get install -y libopenblas-dev + git clone https://github.com/facebookresearch/faiss.git + cd faiss + export faiss_install_path=$PWD/faiss_install + eval "cmake -B build . -DFAISS_ENABLE_PYTHON=OFF -DCMAKE_INSTALL_PREFIX=${faiss_install_path}" + make -C build -j faiss + make -C build install + cd .. +fi + +if [ -d "opencv-3.4.7/opencv3/" ] && [ $(md5sum opencv-3.4.7.tar.gz | awk -F ' ' '{print $1}') = "faa2b5950f8bee3f03118e600c74746a" ];then + echo "################### build opencv skipped ###################" +else + echo "################### build opencv ###################" + rm -rf opencv-3.4.7.tar.gz opencv-3.4.7/ + wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/opencv-3.4.7.tar.gz + tar -xf opencv-3.4.7.tar.gz + + cd opencv-3.4.7/ + install_path=$(pwd)/opencv3 + + rm -rf build + mkdir build + cd build + + cmake .. \ + -DCMAKE_INSTALL_PREFIX=${install_path} \ + -DCMAKE_BUILD_TYPE=Release \ + -DBUILD_SHARED_LIBS=OFF \ + -DWITH_IPP=OFF \ + -DBUILD_IPP_IW=OFF \ + -DWITH_LAPACK=OFF \ + -DWITH_EIGEN=OFF \ + -DCMAKE_INSTALL_LIBDIR=lib64 \ + -DWITH_ZLIB=ON \ + -DBUILD_ZLIB=ON \ + -DWITH_JPEG=ON \ + -DBUILD_JPEG=ON \ + -DWITH_PNG=ON \ + -DBUILD_PNG=ON \ + -DWITH_TIFF=ON \ + -DBUILD_TIFF=ON + + make -j + make install + cd ../../ + echo "################### build opencv finished ###################" +fi + +echo "################### build PaddleClas demo ####################" +OPENCV_DIR=$(pwd)/opencv-3.4.7/opencv3/ +# LIB_DIR=/work/project/project/test/paddle_inference/ +LIB_DIR=$(pwd)/Paddle/build/paddle_inference_install_dir/ +CUDA_LIB_DIR=$(dirname `find /usr -name libcudart.so`) +CUDNN_LIB_DIR=$(dirname `find /usr -name libcudnn.so`) + +BUILD_DIR=build +rm -rf ${BUILD_DIR} +mkdir ${BUILD_DIR} +cd ${BUILD_DIR} +if [[ $cpp_infer_type == cls ]]; then + cmake .. \ + -DPADDLE_LIB=${LIB_DIR} \ + -DWITH_MKL=ON \ + -DWITH_GPU=ON \ + -DWITH_STATIC_LIB=OFF \ + -DWITH_TENSORRT=OFF \ + -DOPENCV_DIR=${OPENCV_DIR} \ + -DCUDNN_LIB=${CUDNN_LIB_DIR} \ + -DCUDA_LIB=${CUDA_LIB_DIR} \ + -DTENSORRT_DIR=${TENSORRT_DIR} +else + cmake ..\ + -DPADDLE_LIB=${LIB_DIR} \ + -DWITH_MKL=ON \ + -DWITH_GPU=ON \ + -DWITH_STATIC_LIB=OFF \ + -DWITH_TENSORRT=OFF \ + -DOPENCV_DIR=${OPENCV_DIR} \ + -DCUDNN_LIB=${CUDNN_LIB_DIR} \ + -DCUDA_LIB=${CUDA_LIB_DIR} \ + -DTENSORRT_DIR=${TENSORRT_DIR} \ + -DFAISS_DIR=${faiss_install_path} \ + -DFAISS_WITH_MKL=OFF +fi +make -j +cd ../../../ +# cd ../../ +echo "################### build PaddleClas demo finished ###################" + + +# set cuda device +# GPUID=$2 +# if [ ${#GPUID} -le 0 ];then +# env="export CUDA_VISIBLE_DEVICES=0" +# else +# env="export CUDA_VISIBLE_DEVICES=${GPUID}" +# fi +# set CUDA_VISIBLE_DEVICES +# eval $env + + +echo "################### run test ###################" +export Count=0 +IFS="|" +infer_quant_flag=(${cpp_infer_is_quant}) +for infer_model in ${cpp_infer_model_dir[*]}; do + #run inference + is_quant=${infer_quant_flag[Count]} + if [[ $cpp_infer_type == "cls" ]]; then + func_cls_cpp_inference "${inference_cmd}" "${infer_model}" "${LOG_PATH}" "${cpp_image_dir_value}" ${is_quant} + else + func_shitu_cpp_inference "${inference_cmd}" "${infer_model}" "${LOG_PATH}" "${cpp_image_dir_value}" ${is_quant} + fi + Count=$(($Count + 1)) +done diff --git a/src/PaddleClas/test_tipc/test_inference_jeston.sh b/src/PaddleClas/test_tipc/test_inference_jeston.sh new file mode 100644 index 0000000..2fd76e1 --- /dev/null +++ b/src/PaddleClas/test_tipc/test_inference_jeston.sh @@ -0,0 +1,87 @@ +#!/bin/bash +source test_tipc/common_func.sh +source test_tipc/test_train_inference_python.sh + +FILENAME=$1 +# MODE be one of ['whole_infer'] +MODE=$2 + +dataline=$(awk 'NR==1, NR==17{print}' $FILENAME) + +# parser params +IFS=$'\n' +lines=(${dataline}) + +model_name=$(func_parser_value "${lines[1]}") +python=$(func_parser_value "${lines[2]}") + +infer_model_dir_list=$(func_parser_value "${lines[3]}") +infer_export_list=$(func_parser_value "${lines[4]}") +infer_is_quant=$(func_parser_value "${lines[5]}") +# parser inference +inference_py=$(func_parser_value "${lines[6]}") +use_gpu_key=$(func_parser_key "${lines[7]}") +use_gpu_list=$(func_parser_value "${lines[7]}") +use_mkldnn_key=$(func_parser_key "${lines[8]}") +use_mkldnn_list=$(func_parser_value "${lines[8]}") +cpu_threads_key=$(func_parser_key "${lines[9]}") +cpu_threads_list=$(func_parser_value "${lines[9]}") +batch_size_key=$(func_parser_key "${lines[10]}") +batch_size_list=$(func_parser_value "${lines[10]}") +use_trt_key=$(func_parser_key "${lines[11]}") +use_trt_list=$(func_parser_value "${lines[11]}") +precision_key=$(func_parser_key "${lines[12]}") +precision_list=$(func_parser_value "${lines[12]}") +infer_model_key=$(func_parser_key "${lines[13]}") +image_dir_key=$(func_parser_key "${lines[14]}") +infer_img_dir=$(func_parser_value "${lines[14]}") +save_log_key=$(func_parser_key "${lines[15]}") +benchmark_key=$(func_parser_key "${lines[16]}") +benchmark_value=$(func_parser_value "${lines[16]}") +infer_key1=$(func_parser_key "${lines[17]}") +infer_value1=$(func_parser_value "${lines[17]}") + + +LOG_PATH="./test_tipc/output" +mkdir -p ${LOG_PATH} +status_log="${LOG_PATH}/results_python.log" + + +if [ ${MODE} = "whole_infer" ]; then + GPUID=$3 + if [ ${#GPUID} -le 0 ];then + env=" " + else + env="export CUDA_VISIBLE_DEVICES=${GPUID}" + fi + # set CUDA_VISIBLE_DEVICES + eval $env + export Count=0 + IFS="|" + infer_run_exports=(${infer_export_list}) + infer_quant_flag=(${infer_is_quant}) + for infer_model in ${infer_model_dir_list[*]}; do + # run export + if [ ${infer_run_exports[Count]} != "null" ];then + save_infer_dir=$(dirname $infer_model) + set_export_weight=$(func_set_params "${export_weight}" "${infer_model}") + set_save_infer_key=$(func_set_params "${save_infer_key}" "${save_infer_dir}") + export_cmd="${python} ${infer_run_exports[Count]} ${set_export_weight} ${set_save_infer_key}" + echo ${infer_run_exports[Count]} + echo $export_cmd + eval $export_cmd + status_export=$? + status_check $status_export "${export_cmd}" "${status_log}" + else + save_infer_dir=${infer_model} + fi + #run inference + is_quant=${infer_quant_flag[Count]} + if [ ${MODE} = "klquant_infer" ]; then + is_quant="True" + fi + func_inference "${python}" "${inference_py}" "${save_infer_dir}" "${LOG_PATH}" "${infer_img_dir}" ${is_quant} + Count=$(($Count + 1)) + done +fi + diff --git a/src/PaddleClas/test_tipc/test_lite_arm_cpp.sh b/src/PaddleClas/test_tipc/test_lite_arm_cpp.sh new file mode 100644 index 0000000..c071a23 --- /dev/null +++ b/src/PaddleClas/test_tipc/test_lite_arm_cpp.sh @@ -0,0 +1,159 @@ +#!/bin/bash +source ./common_func.sh +export LD_LIBRARY_PATH=${PWD}:$LD_LIBRARY_PATH + +FILENAME=$1 +dataline=$(cat $FILENAME) +# parser params +IFS=$'\n' +lines=(${dataline}) + +# parser lite inference +inference_cmd=$(func_parser_value "${lines[1]}") +runtime_device=$(func_parser_value "${lines[2]}") +det_model_list=$(func_parser_value "${lines[3]}") +rec_model_list=$(func_parser_value "${lines[4]}") +cls_model_list=$(func_parser_value "${lines[5]}") +cpu_threads_list=$(func_parser_value "${lines[6]}") +det_batch_size_list=$(func_parser_value "${lines[7]}") +rec_batch_size_list=$(func_parser_value "${lines[8]}") +infer_img_dir_list=$(func_parser_value "${lines[9]}") +config_dir=$(func_parser_value "${lines[10]}") +rec_dict_dir=$(func_parser_value "${lines[11]}") +benchmark_value=$(func_parser_value "${lines[12]}") + +if [[ $inference_cmd =~ "det" ]]; then + lite_model_list=${det_lite_model_list} +elif [[ $inference_cmd =~ "rec" ]]; then + lite_model_list=(${rec_lite_model_list[*]} ${cls_lite_model_list[*]}) +elif [[ $inference_cmd =~ "system" ]]; then + lite_model_list=(${det_lite_model_list[*]} ${rec_lite_model_list[*]} ${cls_lite_model_list[*]}) +else + echo "inference_cmd is wrong, please check." + exit 1 +fi + +LOG_PATH="./output" +mkdir -p ${LOG_PATH} +status_log="${LOG_PATH}/results.log" + + +function func_test_det(){ + IFS='|' + _script=$1 + _det_model=$2 + _log_path=$3 + _img_dir=$4 + _config=$5 + if [[ $_det_model =~ "slim" ]]; then + precision="INT8" + else + precision="FP32" + fi + + # lite inference + for num_threads in ${cpu_threads_list[*]}; do + for det_batchsize in ${det_batch_size_list[*]}; do + _save_log_path="${_log_path}/lite_${_det_model}_runtime_device_${runtime_device}_precision_${precision}_det_batchsize_${det_batchsize}_threads_${num_threads}.log" + command="${_script} ${_det_model} ${runtime_device} ${precision} ${num_threads} ${det_batchsize} ${_img_dir} ${_config} ${benchmark_value} > ${_save_log_path} 2>&1" + eval ${command} + status_check $? "${command}" "${status_log}" + done + done +} + +function func_test_rec(){ + IFS='|' + _script=$1 + _rec_model=$2 + _cls_model=$3 + _log_path=$4 + _img_dir=$5 + _config=$6 + _rec_dict_dir=$7 + + if [[ $_det_model =~ "slim" ]]; then + _precision="INT8" + else + _precision="FP32" + fi + + # lite inference + for num_threads in ${cpu_threads_list[*]}; do + for rec_batchsize in ${rec_batch_size_list[*]}; do + _save_log_path="${_log_path}/lite_${_rec_model}_${cls_model}_runtime_device_${runtime_device}_precision_${_precision}_rec_batchsize_${rec_batchsize}_threads_${num_threads}.log" + command="${_script} ${_rec_model} ${_cls_model} ${runtime_device} ${_precision} ${num_threads} ${rec_batchsize} ${_img_dir} ${_config} ${_rec_dict_dir} ${benchmark_value} > ${_save_log_path} 2>&1" + eval ${command} + status_check $? "${command}" "${status_log}" + done + done +} + +function func_test_system(){ + IFS='|' + _script=$1 + _det_model=$2 + _rec_model=$3 + _cls_model=$4 + _log_path=$5 + _img_dir=$6 + _config=$7 + _rec_dict_dir=$8 + if [[ $_det_model =~ "slim" ]]; then + _precision="INT8" + else + _precision="FP32" + fi + + # lite inference + for num_threads in ${cpu_threads_list[*]}; do + for det_batchsize in ${det_batch_size_list[*]}; do + for rec_batchsize in ${rec_batch_size_list[*]}; do + _save_log_path="${_log_path}/lite_${_det_model}_${_rec_model}_${_cls_model}_runtime_device_${runtime_device}_precision_${_precision}_det_batchsize_${det_batchsize}_rec_batchsize_${rec_batchsize}_threads_${num_threads}.log" + command="${_script} ${_det_model} ${_rec_model} ${_cls_model} ${runtime_device} ${_precision} ${num_threads} ${det_batchsize} ${_img_dir} ${_config} ${_rec_dict_dir} ${benchmark_value} > ${_save_log_path} 2>&1" + eval ${command} + status_check $? "${command}" "${status_log}" + done + done + done +} + + +echo "################### run test ###################" + +if [[ $inference_cmd =~ "det" ]]; then + IFS="|" + det_model_list=(${det_model_list[*]}) + + for i in {0..1}; do + #run lite inference + for img_dir in ${infer_img_dir_list[*]}; do + func_test_det "${inference_cmd}" "${det_model_list[i]}_opt.nb" "${LOG_PATH}" "${img_dir}" "${config_dir}" + done + done + +elif [[ $inference_cmd =~ "rec" ]]; then + IFS="|" + rec_model_list=(${rec_model_list[*]}) + cls_model_list=(${cls_model_list[*]}) + + for i in {0..1}; do + #run lite inference + for img_dir in ${infer_img_dir_list[*]}; do + func_test_rec "${inference_cmd}" "${rec_model}_opt.nb" "${cls_model_list[i]}_opt.nb" "${LOG_PATH}" "${img_dir}" "${rec_dict_dir}" "${config_dir}" + done + done + +elif [[ $inference_cmd =~ "system" ]]; then + IFS="|" + det_model_list=(${det_model_list[*]}) + rec_model_list=(${rec_model_list[*]}) + cls_model_list=(${cls_model_list[*]}) + + for i in {0..1}; do + #run lite inference + for img_dir in ${infer_img_dir_list[*]}; do + func_test_system "${inference_cmd}" "${det_model_list[i]}_opt.nb" "${rec_model_list[i]}_opt.nb" "${cls_model_list[i]}_opt.nb" "${LOG_PATH}" "${img_dir}" "${config_dir}" "${rec_dict_dir}" + done + done +fi diff --git a/src/PaddleClas/test_tipc/test_paddle2onnx.sh b/src/PaddleClas/test_tipc/test_paddle2onnx.sh new file mode 100644 index 0000000..850fc90 --- /dev/null +++ b/src/PaddleClas/test_tipc/test_paddle2onnx.sh @@ -0,0 +1,78 @@ +#!/bin/bash +source test_tipc/common_func.sh + +FILENAME=$1 + +dataline=$(cat ${FILENAME}) +lines=(${dataline}) +# common params +model_name=$(func_parser_value "${lines[1]}") +python=$(func_parser_value "${lines[2]}") + + +# parser params +dataline=$(awk 'NR==1, NR==14{print}' $FILENAME) +IFS=$'\n' +lines=(${dataline}) + +# parser paddle2onnx +model_name=$(func_parser_value "${lines[1]}") +python=$(func_parser_value "${lines[2]}") +padlle2onnx_cmd=$(func_parser_value "${lines[3]}") +infer_model_dir_key=$(func_parser_key "${lines[4]}") +infer_model_dir_value=$(func_parser_value "${lines[4]}") +model_filename_key=$(func_parser_key "${lines[5]}") +model_filename_value=$(func_parser_value "${lines[5]}") +params_filename_key=$(func_parser_key "${lines[6]}") +params_filename_value=$(func_parser_value "${lines[6]}") +save_file_key=$(func_parser_key "${lines[7]}") +save_file_value=$(func_parser_value "${lines[7]}") +opset_version_key=$(func_parser_key "${lines[8]}") +opset_version_value=$(func_parser_value "${lines[8]}") +enable_onnx_checker_key=$(func_parser_key "${lines[9]}") +enable_onnx_checker_value=$(func_parser_value "${lines[9]}") +# parser onnx inference +inference_py=$(func_parser_value "${lines[10]}") +use_onnx_key=$(func_parser_key "${lines[11]}") +use_onnx_value=$(func_parser_value "${lines[11]}") +inference_model_dir_key=$(func_parser_key "${lines[12]}") +inference_model_dir_value=$(func_parser_value "${lines[12]}") +inference_hardware_key=$(func_parser_key "${lines[13]}") +inference_hardware_value=$(func_parser_value "${lines[13]}") + +LOG_PATH="./test_tipc/output" +mkdir -p ./test_tipc/output +status_log="${LOG_PATH}/results_paddle2onnx.log" + + +function func_paddle2onnx(){ + IFS='|' + _script=$1 + + # paddle2onnx + _save_log_path=".${LOG_PATH}/paddle2onnx_infer_cpu.log" + set_dirname=$(func_set_params "${infer_model_dir_key}" "${infer_model_dir_value}") + set_model_filename=$(func_set_params "${model_filename_key}" "${model_filename_value}") + set_params_filename=$(func_set_params "${params_filename_key}" "${params_filename_value}") + set_save_model=$(func_set_params "${save_file_key}" "${save_file_value}") + set_opset_version=$(func_set_params "${opset_version_key}" "${opset_version_value}") + set_enable_onnx_checker=$(func_set_params "${enable_onnx_checker_key}" "${enable_onnx_checker_value}") + trans_model_cmd="${padlle2onnx_cmd} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_save_model} ${set_opset_version} ${set_enable_onnx_checker}" + eval $trans_model_cmd + last_status=${PIPESTATUS[0]} + status_check $last_status "${trans_model_cmd}" "${status_log}" + # python inference + set_model_dir=$(func_set_params "${inference_model_dir_key}" "${inference_model_dir_value}") + set_use_onnx=$(func_set_params "${use_onnx_key}" "${use_onnx_value}") + set_hardware=$(func_set_params "${inference_hardware_key}" "${inference_hardware_value}") + infer_model_cmd="cd deploy && ${python} ${inference_py} -o ${set_model_dir} -o ${set_use_onnx} -o ${set_hardware} >${_save_log_path} 2>&1 && cd ../" + eval $infer_model_cmd + status_check $last_status "${infer_model_cmd}" "${status_log}" +} + + +echo "################### run test ###################" + +export Count=0 +IFS="|" +func_paddle2onnx \ No newline at end of file diff --git a/src/PaddleClas/test_tipc/test_serving.sh b/src/PaddleClas/test_tipc/test_serving.sh new file mode 100644 index 0000000..c36935a --- /dev/null +++ b/src/PaddleClas/test_tipc/test_serving.sh @@ -0,0 +1,168 @@ +#!/bin/bash +source test_tipc/common_func.sh + +FILENAME=$1 +dataline=$(awk 'NR==1, NR==18{print}' $FILENAME) + +# parser params +IFS=$'\n' +lines=(${dataline}) + +# parser serving +model_name=$(func_parser_value "${lines[1]}") +python=$(func_parser_value "${lines[2]}") +trans_model_py=$(func_parser_value "${lines[3]}") +infer_model_dir_key=$(func_parser_key "${lines[4]}") +infer_model_dir_value=$(func_parser_value "${lines[4]}") +model_filename_key=$(func_parser_key "${lines[5]}") +model_filename_value=$(func_parser_value "${lines[5]}") +params_filename_key=$(func_parser_key "${lines[6]}") +params_filename_value=$(func_parser_value "${lines[6]}") +serving_server_key=$(func_parser_key "${lines[7]}") +serving_server_value=$(func_parser_value "${lines[7]}") +serving_client_key=$(func_parser_key "${lines[8]}") +serving_client_value=$(func_parser_value "${lines[8]}") +serving_dir_value=$(func_parser_value "${lines[9]}") +web_service_py=$(func_parser_value "${lines[10]}") +web_use_gpu_key=$(func_parser_key "${lines[11]}") +web_use_gpu_list=$(func_parser_value "${lines[11]}") +web_use_mkldnn_key=$(func_parser_key "${lines[12]}") +web_use_mkldnn_list=$(func_parser_value "${lines[12]}") +web_cpu_threads_key=$(func_parser_key "${lines[13]}") +web_cpu_threads_list=$(func_parser_value "${lines[13]}") +web_use_trt_key=$(func_parser_key "${lines[14]}") +web_use_trt_list=$(func_parser_value "${lines[14]}") +web_precision_key=$(func_parser_key "${lines[15]}") +web_precision_list=$(func_parser_value "${lines[15]}") +pipeline_py=$(func_parser_value "${lines[16]}") +image_dir_key=$(func_parser_key "${lines[17]}") +image_dir_value=$(func_parser_value "${lines[17]}") + +LOG_PATH="../../test_tipc/output" +mkdir -p ./test_tipc/output +status_log="${LOG_PATH}/results_serving.log" + +function func_serving(){ + IFS='|' + _python=$1 + _script=$2 + _model_dir=$3 + # pdserving + set_dirname=$(func_set_params "${infer_model_dir_key}" "${infer_model_dir_value}") + set_model_filename=$(func_set_params "${model_filename_key}" "${model_filename_value}") + set_params_filename=$(func_set_params "${params_filename_key}" "${params_filename_value}") + set_serving_server=$(func_set_params "${serving_server_key}" "${serving_server_value}") + set_serving_client=$(func_set_params "${serving_client_key}" "${serving_client_value}") + set_image_dir=$(func_set_params "${image_dir_key}" "${image_dir_value}") + trans_model_cmd="${python} ${trans_model_py} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_serving_server} ${set_serving_client}" + eval $trans_model_cmd + cd ${serving_dir_value} + echo $PWD + unset https_proxy + unset http_proxy + for python in ${python[*]}; do + if [ ${python} = "cpp"]; then + for use_gpu in ${web_use_gpu_list[*]}; do + if [ ${use_gpu} = "null" ]; then + web_service_cpp_cmd="${python} -m paddle_serving_server.serve --model ppocr_det_mobile_2.0_serving/ ppocr_rec_mobile_2.0_serving/ --port 9293" + eval $web_service_cmd + sleep 2s + _save_log_path="${LOG_PATH}/server_infer_cpp_cpu_pipeline_usemkldnn_False_threads_4_batchsize_1.log" + pipeline_cmd="${python} ocr_cpp_client.py ppocr_det_mobile_2.0_client/ ppocr_rec_mobile_2.0_client/" + eval $pipeline_cmd + status_check $last_status "${pipeline_cmd}" "${status_log}" + sleep 2s + ps ux | grep -E 'web_service|pipeline' | awk '{print $2}' | xargs kill -s 9 + else + web_service_cpp_cmd="${python} -m paddle_serving_server.serve --model ppocr_det_mobile_2.0_serving/ ppocr_rec_mobile_2.0_serving/ --port 9293 --gpu_id=0" + eval $web_service_cmd + sleep 2s + _save_log_path="${LOG_PATH}/server_infer_cpp_cpu_pipeline_usemkldnn_False_threads_4_batchsize_1.log" + pipeline_cmd="${python} ocr_cpp_client.py ppocr_det_mobile_2.0_client/ ppocr_rec_mobile_2.0_client/" + eval $pipeline_cmd + status_check $last_status "${pipeline_cmd}" "${status_log}" + sleep 2s + ps ux | grep -E 'web_service|pipeline' | awk '{print $2}' | xargs kill -s 9 + fi + done + else + # python serving + for use_gpu in ${web_use_gpu_list[*]}; do + echo ${ues_gpu} + if [ ${use_gpu} = "null" ]; then + for use_mkldnn in ${web_use_mkldnn_list[*]}; do + if [ ${use_mkldnn} = "False" ]; then + continue + fi + for threads in ${web_cpu_threads_list[*]}; do + set_cpu_threads=$(func_set_params "${web_cpu_threads_key}" "${threads}") + web_service_cmd="${python} ${web_service_py} ${web_use_gpu_key}=${use_gpu} ${web_use_mkldnn_key}=${use_mkldnn} ${set_cpu_threads} &" + eval $web_service_cmd + sleep 2s + for pipeline in ${pipeline_py[*]}; do + _save_log_path="${LOG_PATH}/server_infer_cpu_${pipeline%_client*}_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_1.log" + pipeline_cmd="${python} ${pipeline} ${set_image_dir} > ${_save_log_path} 2>&1 " + eval $pipeline_cmd + last_status=${PIPESTATUS[0]} + eval "cat ${_save_log_path}" + status_check $last_status "${pipeline_cmd}" "${status_log}" + sleep 2s + done + ps ux | grep -E 'web_service|pipeline' | awk '{print $2}' | xargs kill -s 9 + done + done + elif [ ${use_gpu} = "0" ]; then + for use_trt in ${web_use_trt_list[*]}; do + for precision in ${web_precision_list[*]}; do + if [[ ${_flag_quant} = "False" ]] && [[ ${precision} =~ "int8" ]]; then + continue + fi + if [[ ${precision} =~ "fp16" || ${precision} =~ "int8" ]] && [ ${use_trt} = "False" ]; then + continue + fi + if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [[ ${_flag_quant} = "True" ]]; then + continue + fi + set_tensorrt=$(func_set_params "${web_use_trt_key}" "${use_trt}") + set_precision=$(func_set_params "${web_precision_key}" "${precision}") + web_service_cmd="${python} ${web_service_py} ${web_use_gpu_key}=${use_gpu} ${set_tensorrt} ${set_precision} & " + eval $web_service_cmd + + sleep 2s + for pipeline in ${pipeline_py[*]}; do + _save_log_path="${LOG_PATH}/server_infer_gpu_${pipeline%_client*}_usetrt_${use_trt}_precision_${precision}_batchsize_1.log" + pipeline_cmd="${python} ${pipeline} ${set_image_dir}> ${_save_log_path} 2>&1" + eval $pipeline_cmd + last_status=${PIPESTATUS[0]} + eval "cat ${_save_log_path}" + status_check $last_status "${pipeline_cmd}" "${status_log}" + sleep 2s + done + ps ux | grep -E 'web_service|pipeline' | awk '{print $2}' | xargs kill -s 9 + done + done + else + echo "Does not support hardware other than CPU and GPU Currently!" + fi + done + fi + done +} + + +# set cuda device +GPUID=$2 +if [ ${#GPUID} -le 0 ];then + env=" " +else + env="export CUDA_VISIBLE_DEVICES=${GPUID}" +fi +set CUDA_VISIBLE_DEVICES +eval $env + + +echo "################### run test ###################" + +export Count=0 +IFS="|" +func_serving "${web_service_cmd}" diff --git a/src/PaddleClas/test_tipc/test_train_inference_python.sh b/src/PaddleClas/test_tipc/test_train_inference_python.sh new file mode 100644 index 0000000..39503dd --- /dev/null +++ b/src/PaddleClas/test_tipc/test_train_inference_python.sh @@ -0,0 +1,340 @@ +#!/bin/bash +FILENAME=$1 +source test_tipc/common_func.sh + +# MODE be one of ['lite_train_lite_infer' 'lite_train_whole_infer' 'whole_train_whole_infer', 'whole_infer', 'klquant_whole_infer'] +MODE=$2 + +dataline=$(cat ${FILENAME}) + +# parser params +IFS=$'\n' +lines=(${dataline}) + +# The training params +model_name=$(func_parser_value "${lines[1]}") +python=$(func_parser_value "${lines[2]}") +gpu_list=$(func_parser_value "${lines[3]}") +train_use_gpu_key=$(func_parser_key "${lines[4]}") +train_use_gpu_value=$(func_parser_value "${lines[4]}") +autocast_list=$(func_parser_value "${lines[5]}") +autocast_key=$(func_parser_key "${lines[5]}") +epoch_key=$(func_parser_key "${lines[6]}") +epoch_num=$(func_parser_params "${lines[6]}") +save_model_key=$(func_parser_key "${lines[7]}") +train_batch_key=$(func_parser_key "${lines[8]}") +train_batch_value=$(func_parser_value "${lines[8]}") +pretrain_model_key=$(func_parser_key "${lines[9]}") +pretrain_model_value=$(func_parser_value "${lines[9]}") +train_model_name=$(func_parser_value "${lines[10]}") +train_infer_img_dir=$(func_parser_value "${lines[11]}") +train_param_key1=$(func_parser_key "${lines[12]}") +train_param_value1=$(func_parser_value "${lines[12]}") + +trainer_list=$(func_parser_value "${lines[14]}") +trainer_norm=$(func_parser_key "${lines[15]}") +norm_trainer=$(func_parser_value "${lines[15]}") +pact_key=$(func_parser_key "${lines[16]}") +pact_trainer=$(func_parser_value "${lines[16]}") +fpgm_key=$(func_parser_key "${lines[17]}") +fpgm_trainer=$(func_parser_value "${lines[17]}") +distill_key=$(func_parser_key "${lines[18]}") +distill_trainer=$(func_parser_value "${lines[18]}") +trainer_key1=$(func_parser_key "${lines[19]}") +trainer_value1=$(func_parser_value "${lines[19]}") +trainer_key2=$(func_parser_key "${lines[20]}") +trainer_value2=$(func_parser_value "${lines[20]}") + +eval_py=$(func_parser_value "${lines[23]}") +eval_key1=$(func_parser_key "${lines[24]}") +eval_value1=$(func_parser_value "${lines[24]}") + +save_infer_key=$(func_parser_key "${lines[27]}") +export_weight=$(func_parser_key "${lines[28]}") +norm_export=$(func_parser_value "${lines[29]}") +pact_export=$(func_parser_value "${lines[30]}") +fpgm_export=$(func_parser_value "${lines[31]}") +distill_export=$(func_parser_value "${lines[32]}") +kl_quant_cmd_key=$(func_parser_key "${lines[33]}") +kl_quant_cmd_value=$(func_parser_value "${lines[33]}") +export_key2=$(func_parser_key "${lines[34]}") +export_value2=$(func_parser_value "${lines[34]}") + +# parser inference model +infer_model_dir_list=$(func_parser_value "${lines[36]}") +infer_export_flag=$(func_parser_value "${lines[37]}") +infer_is_quant=$(func_parser_value "${lines[38]}") + +# parser inference +inference_py=$(func_parser_value "${lines[39]}") +use_gpu_key=$(func_parser_key "${lines[40]}") +use_gpu_list=$(func_parser_value "${lines[40]}") +use_mkldnn_key=$(func_parser_key "${lines[41]}") +use_mkldnn_list=$(func_parser_value "${lines[41]}") +cpu_threads_key=$(func_parser_key "${lines[42]}") +cpu_threads_list=$(func_parser_value "${lines[42]}") +batch_size_key=$(func_parser_key "${lines[43]}") +batch_size_list=$(func_parser_value "${lines[43]}") +use_trt_key=$(func_parser_key "${lines[44]}") +use_trt_list=$(func_parser_value "${lines[44]}") +precision_key=$(func_parser_key "${lines[45]}") +precision_list=$(func_parser_value "${lines[45]}") +infer_model_key=$(func_parser_key "${lines[46]}") +image_dir_key=$(func_parser_key "${lines[47]}") +infer_img_dir=$(func_parser_value "${lines[47]}") +save_log_key=$(func_parser_key "${lines[48]}") +benchmark_key=$(func_parser_key "${lines[49]}") +benchmark_value=$(func_parser_value "${lines[49]}") +infer_key1=$(func_parser_key "${lines[50]}") +infer_value1=$(func_parser_value "${lines[50]}") +if [ ! $epoch_num ]; then + epoch_num=2 +fi +LOG_PATH="./test_tipc/output" +mkdir -p ${LOG_PATH} +status_log="${LOG_PATH}/results_python.log" + +function func_inference(){ + IFS='|' + _python=$1 + _script=$2 + _model_dir=$3 + _log_path=$4 + _img_dir=$5 + _flag_quant=$6 + # inference + for use_gpu in ${use_gpu_list[*]}; do + if [ ${use_gpu} = "False" ] || [ ${use_gpu} = "cpu" ]; then + for use_mkldnn in ${use_mkldnn_list[*]}; do + if [ ${use_mkldnn} = "False" ] && [ ${_flag_quant} = "True" ]; then + continue + fi + for threads in ${cpu_threads_list[*]}; do + for batch_size in ${batch_size_list[*]}; do + _save_log_path="${_log_path}/infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_${batch_size}.log" + set_infer_data=$(func_set_params "${image_dir_key}" "${_img_dir}") + set_benchmark=$(func_set_params "${benchmark_key}" "${benchmark_value}") + set_batchsize=$(func_set_params "${batch_size_key}" "${batch_size}") + set_cpu_threads=$(func_set_params "${cpu_threads_key}" "${threads}") + set_model_dir=$(func_set_params "${infer_model_key}" "${_model_dir}") + set_infer_params1=$(func_set_params "${infer_key1}" "${infer_value1}") + command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_mkldnn_key}=${use_mkldnn} ${set_cpu_threads} ${set_model_dir} ${set_batchsize} ${set_infer_data} ${set_benchmark} ${set_infer_params1} > ${_save_log_path} 2>&1 " + eval $command + last_status=${PIPESTATUS[0]} + eval "cat ${_save_log_path}" + status_check $last_status "${command}" "../${status_log}" + done + done + done + elif [ ${use_gpu} = "True" ] || [ ${use_gpu} = "gpu" ]; then + for use_trt in ${use_trt_list[*]}; do + for precision in ${precision_list[*]}; do + if [ ${precision} = "True" ] && [ ${use_trt} = "False" ]; then + continue + fi + if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [ ${_flag_quant} = "True" ]; then + continue + fi + for batch_size in ${batch_size_list[*]}; do + _save_log_path="${_log_path}/infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}.log" + set_infer_data=$(func_set_params "${image_dir_key}" "${_img_dir}") + set_benchmark=$(func_set_params "${benchmark_key}" "${benchmark_value}") + set_batchsize=$(func_set_params "${batch_size_key}" "${batch_size}") + set_tensorrt=$(func_set_params "${use_trt_key}" "${use_trt}") + set_precision=$(func_set_params "${precision_key}" "${precision}") + set_model_dir=$(func_set_params "${infer_model_key}" "${_model_dir}") + command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${set_tensorrt} ${set_precision} ${set_model_dir} ${set_batchsize} ${set_infer_data} ${set_benchmark} > ${_save_log_path} 2>&1 " + eval $command + last_status=${PIPESTATUS[0]} + eval "cat ${_save_log_path}" + status_check $last_status "${command}" "../${status_log}" + done + done + done + else + echo "Does not support hardware other than CPU and GPU Currently!" + fi + done +} + +if [ ${MODE} = "whole_infer" ] || [ ${MODE} = "klquant_whole_infer" ]; then + IFS="|" + infer_export_flag=(${infer_export_flag}) + if [ ${infer_export_flag} != "null" ] && [ ${infer_export_flag} != "False" ]; then + rm -rf ${infer_model_dir_list/..\//} + export_cmd="${python} ${norm_export} -o Global.pretrained_model=${model_name}_pretrained -o Global.save_inference_dir=${infer_model_dir_list/..\//}" + eval $export_cmd + fi +fi + +if [ ${MODE} = "whole_infer" ]; then + GPUID=$3 + if [ ${#GPUID} -le 0 ];then + env=" " + else + env="export CUDA_VISIBLE_DEVICES=${GPUID}" + fi + # set CUDA_VISIBLE_DEVICES + eval $env + export Count=0 + cd deploy + for infer_model in ${infer_model_dir_list[*]}; do + #run inference + is_quant=${infer_quant_flag[Count]} + echo "is_quant: ${is_quant}" + func_inference "${python}" "${inference_py}" "${infer_model}" "../${LOG_PATH}" "${infer_img_dir}" ${is_quant} + Count=$(($Count + 1)) + done + cd .. + +elif [ ${MODE} = "klquant_whole_infer" ]; then + # for kl_quant + if [ ${kl_quant_cmd_value} != "null" ] && [ ${kl_quant_cmd_value} != "False" ]; then + echo "kl_quant" + command="${python} ${kl_quant_cmd_value}" + eval $command + last_status=${PIPESTATUS[0]} + status_check $last_status "${command}" "${status_log}" + cd inference/quant_post_static_model + ln -s __model__ inference.pdmodel + ln -s __params__ inference.pdiparams + cd ../../deploy + is_quant=True + func_inference "${python}" "${inference_py}" "${infer_model_dir_list}/quant_post_static_model" "../${LOG_PATH}" "${infer_img_dir}" ${is_quant} + cd .. + fi +else + IFS="|" + export Count=0 + USE_GPU_KEY=(${train_use_gpu_value}) + for gpu in ${gpu_list[*]}; do + train_use_gpu=${USE_GPU_KEY[Count]} + Count=$(($Count + 1)) + ips="" + if [ ${gpu} = "-1" ];then + env="" + elif [ ${#gpu} -le 1 ];then + env="export CUDA_VISIBLE_DEVICES=${gpu}" + eval ${env} + elif [ ${#gpu} -le 15 ];then + IFS="," + array=(${gpu}) + env="export CUDA_VISIBLE_DEVICES=${array[0]}" + IFS="|" + else + IFS=";" + array=(${gpu}) + ips=${array[0]} + gpu=${array[1]} + IFS="|" + env=" " + fi + for autocast in ${autocast_list[*]}; do + for trainer in ${trainer_list[*]}; do + flag_quant=False + if [ ${trainer} = ${pact_key} ]; then + run_train=${pact_trainer} + run_export=${pact_export} + flag_quant=True + elif [ ${trainer} = "${fpgm_key}" ]; then + run_train=${fpgm_trainer} + run_export=${fpgm_export} + elif [ ${trainer} = "${distill_key}" ]; then + run_train=${distill_trainer} + run_export=${distill_export} + elif [ ${trainer} = ${trainer_key1} ]; then + run_train=${trainer_value1} + run_export=${export_value1} + elif [[ ${trainer} = ${trainer_key2} ]]; then + run_train=${trainer_value2} + run_export=${export_value2} + else + run_train=${norm_trainer} + run_export=${norm_export} + fi + + if [ ${run_train} = "null" ]; then + continue + fi + + set_autocast=$(func_set_params "${autocast_key}" "${autocast}") + set_epoch=$(func_set_params "${epoch_key}" "${epoch_num}") + set_pretrain=$(func_set_params "${pretrain_model_key}" "${pretrain_model_value}") + set_batchsize=$(func_set_params "${train_batch_key}" "${train_batch_value}") + set_train_params1=$(func_set_params "${train_param_key1}" "${train_param_value1}") + set_use_gpu=$(func_set_params "${train_use_gpu_key}" "${train_use_gpu_value}") + if [ ${#ips} -le 26 ];then + save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}" + nodes=1 + else + IFS="," + ips_array=(${ips}) + IFS="|" + nodes=${#ips_array[@]} + save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}_nodes_${nodes}" + fi + + # load pretrain from norm training if current trainer is pact or fpgm trainer + # if [ ${trainer} = ${pact_key} ] || [ ${trainer} = ${fpgm_key} ]; then + # set_pretrain="${load_norm_train_model}" + # fi + + set_save_model=$(func_set_params "${save_model_key}" "${save_log}") + if [ ${#gpu} -le 2 ];then # train with cpu or single gpu + cmd="${python} ${run_train} ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} " + elif [ ${#ips} -le 26 ];then # train with multi-gpu + cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1}" + else # train with multi-machine + cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${set_use_gpu} ${set_save_model} ${set_pretrain} ${set_epoch} ${set_autocast} ${set_batchsize} ${set_train_params1}" + fi + # run train + eval "unset CUDA_VISIBLE_DEVICES" + export FLAGS_cudnn_deterministic=True + sleep 5 + eval $cmd + status_check $? "${cmd}" "${status_log}" + sleep 5 + + if [[ $FILENAME == *GeneralRecognition* ]]; then + set_eval_pretrain=$(func_set_params "${pretrain_model_key}" "${save_log}/RecModel/${train_model_name}") + else + set_eval_pretrain=$(func_set_params "${pretrain_model_key}" "${save_log}/${model_name}/${train_model_name}") + fi + # save norm trained models to set pretrain for pact training and fpgm training + if [ ${trainer} = ${trainer_norm} ]; then + load_norm_train_model=${set_eval_pretrain} + fi + # run eval + if [ ${eval_py} != "null" ]; then + set_eval_params1=$(func_set_params "${eval_key1}" "${eval_value1}") + eval_cmd="${python} ${eval_py} ${set_eval_pretrain} ${set_use_gpu} ${set_eval_params1}" + eval $eval_cmd + status_check $? "${eval_cmd}" "${status_log}" + sleep 5 + fi + # run export model + if [ ${run_export} != "null" ]; then + # run export model + save_infer_path="${save_log}" + if [[ $FILENAME == *GeneralRecognition* ]]; then + set_eval_pretrain=$(func_set_params "${pretrain_model_key}" "${save_log}/RecModel/${train_model_name}") + else + set_export_weight=$(func_set_params "${export_weight}" "${save_log}/${model_name}/${train_model_name}") + fi + set_save_infer_key=$(func_set_params "${save_infer_key}" "${save_infer_path}") + export_cmd="${python} ${run_export} ${set_export_weight} ${set_save_infer_key}" + eval $export_cmd + status_check $? "${export_cmd}" "${status_log}" + + #run inference + eval $env + save_infer_path="${save_log}" + cd deploy + func_inference "${python}" "${inference_py}" "../${save_infer_path}" "../${LOG_PATH}" "${infer_img_dir}" "${flag_quant}" + cd .. + fi + eval "unset CUDA_VISIBLE_DEVICES" + done # done with: for trainer in ${trainer_list[*]}; do + done # done with: for autocast in ${autocast_list[*]}; do + done # done with: for gpu in ${gpu_list[*]}; do +fi # end if [ ${MODE} = "infer" ]; then