diff --git a/doc/实践考评-智能导盲杖软件系统实践的汇报.pptx b/doc/实践考评-智能导盲杖软件系统实践的汇报.pptx index c32ea39..f5f39a4 100644 Binary files a/doc/实践考评-智能导盲杖软件系统实践的汇报.pptx and b/doc/实践考评-智能导盲杖软件系统实践的汇报.pptx differ diff --git a/doc/软件开发项目的个人自评报告-智能导盲杖.xlsx b/doc/软件开发项目的个人自评报告-智能导盲杖.xlsx index ba49a1c..4c48677 100644 Binary files a/doc/软件开发项目的个人自评报告-智能导盲杖.xlsx and b/doc/软件开发项目的个人自评报告-智能导盲杖.xlsx differ diff --git a/src/image_recognition/train.py b/src/image_recognition/train.py index 34b57be..c652328 100644 --- a/src/image_recognition/train.py +++ b/src/image_recognition/train.py @@ -1,10 +1,3 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Train a YOLOv5 model on a custom dataset - -Usage: - $ python path/to/train.py --data coco128.yaml --weights yolov5s.pt --img 640 -""" import argparse import math import os @@ -55,12 +48,12 @@ RANK = int(os.getenv('RANK', -1)) WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1)) -def train(hyp, # 'path/to/hyp.yaml' 或 hyp 字典 +def train(hyp, opt, device, callbacks ): - # 定义训练过程中使用的变量 + # 定义训练过程中使用的变量,启动深度学习模型的训练过程 save_dir, epochs, batch_size, weights, single_cls, evolve, data, cfg, resume, noval, nosave, workers, freeze = \ Path(opt.save_dir), opt.epochs, opt.batch_size, opt.weights, opt.single_cls, opt.evolve, opt.data, opt.cfg, \ opt.resume, opt.noval, opt.nosave, opt.workers, opt.freeze @@ -72,9 +65,9 @@ def train(hyp, # 'path/to/hyp.yaml' 或 hyp 字典 # 超参数 if isinstance(hyp, str): - with open(hyp, errors='ignore') as f: + with open(hyp, errors='ignore') as f:#使用with打开，如果遇到编码错误，就忽略并继续打开 hyp = yaml.safe_load(f) # 加载超参数字典 - LOGGER.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items())) + LOGGER.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items()))#日志，生成字符串 # 保存运行设置 with open(save_dir / 'hyp.yaml', 'w') as f: @@ -82,7 +75,7 @@ def train(hyp, # 'path/to/hyp.yaml' 或 hyp 字典 with open(save_dir / 'opt.yaml', 'w') as f: yaml.safe_dump(vars(opt), f, sort_keys=False) - # Loggers + # 日志记录和初始化 if RANK in [-1, 0]: loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance if loggers.wandb: @@ -90,24 +83,24 @@ def train(hyp, # 'path/to/hyp.yaml' 或 hyp 字典 if resume: weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp - # Register actions + # 注册回调函数 for k in methods(loggers): callbacks.register_action(k, callback=getattr(loggers, k)) - # Config - plots = not evolve # create plots + # 初始化设置 + plots = not evolve # 是否画图 cuda = device.type != 'cpu' - init_seeds(1 + RANK) + init_seeds(1 + RANK) #随机种子 with torch_distributed_zero_first(LOCAL_RANK): - data_dict = data_dict or check_dataset(data) # check if None + data_dict = data_dict or check_dataset(data) # 检查是否存在 train_path, val_path = data_dict['train'], data_dict['val'] - nc = 1 if single_cls else int(data_dict['nc']) # number of classes - names = ['item'] if single_cls and len(data_dict['names']) != 1 else data_dict['names'] # class names - assert len(names) == nc, f'{len(names)} names found for nc={nc} dataset in {data}' # check - is_coco = isinstance(val_path, str) and val_path.endswith('coco/val2017.txt') # COCO dataset + nc = 1 if single_cls else int(data_dict['nc']) # 类别数量 + names = ['item'] if single_cls and len(data_dict['names']) != 1 else data_dict['names'] # 名称 + assert len(names) == nc, f'{len(names)} names found for nc={nc} dataset in {data}' # 检查数量与data_dict是否相匹配 + is_coco = isinstance(val_path, str) and val_path.endswith('coco/val2017.txt') # COCO数据集路径 - # Model - check_suffix(weights, '.pt') # check weights + # 训练模型 + check_suffix(weights, '.pt') # 检查权重文件的后缀 pretrained = weights.endswith('.pt') if pretrained: with torch_distributed_zero_first(LOCAL_RANK): @@ -122,7 +115,7 @@ def train(hyp, # 'path/to/hyp.yaml' 或 hyp 字典 else: model = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create - # Freeze + # 冻结模型层 freeze = [f'model.{x}.' for x in range(freeze)] # layers to freeze for k, v in model.named_parameters(): v.requires_grad = True # train all layers @@ -130,21 +123,21 @@ def train(hyp, # 'path/to/hyp.yaml' 或 hyp 字典 LOGGER.info(f'freezing {k}') v.requires_grad = False - # Image size - gs = max(int(model.stride.max()), 32) # grid size (max stride) - imgsz = check_img_size(opt.imgsz, gs, floor=gs * 2) # verify imgsz is gs-multiple + # 图像和网格尺寸 + gs = max(int(model.stride.max()), 32) # 最小为32 + imgsz = check_img_size(opt.imgsz, gs, floor=gs * 2) # 图像尺寸是网格的整数倍 - # Batch size - if RANK == -1 and batch_size == -1: # single-GPU only, estimate best batch size + # 批量大小 + if RANK == -1 and batch_size == -1: # 单GPU，没有指定批量大小 batch_size = check_train_batch_size(model, imgsz) - # Optimizer - nbs = 64 # nominal batch size - accumulate = max(round(nbs / batch_size), 1) # accumulate loss before optimizing - hyp['weight_decay'] *= batch_size * accumulate / nbs # scale weight_decay + # 优化 + nbs = 64 # 基准 + accumulate = max(round(nbs / batch_size), 1) + hyp['weight_decay'] *= batch_size * accumulate / nbs # 调整权重系数 LOGGER.info(f"Scaled weight_decay = {hyp['weight_decay']}") - g0, g1, g2 = [], [], [] # optimizer parameter groups + g0, g1, g2 = [], [], [] # 初始化3个列表 for v in model.modules(): if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter): # bias g2.append(v.bias) @@ -153,25 +146,25 @@ def train(hyp, # 'path/to/hyp.yaml' 或 hyp 字典 elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter): # weight (with decay) g1.append(v.weight) - if opt.adam: - optimizer = Adam(g0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum + if opt.adam:#选择优化器 + optimizer = Adam(g0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) else: optimizer = SGD(g0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True) - optimizer.add_param_group({'params': g1, 'weight_decay': hyp['weight_decay']}) # add g1 with weight_decay - optimizer.add_param_group({'params': g2}) # add g2 (biases) + optimizer.add_param_group({'params': g1, 'weight_decay': hyp['weight_decay']}) # 添加g1 使用权重衰减 + optimizer.add_param_group({'params': g2}) # 添加g2，不使用权重衰减 LOGGER.info(f"{colorstr('optimizer:')} {type(optimizer).__name__} with parameter groups " f"{len(g0)} weight, {len(g1)} weight (no decay), {len(g2)} bias") - del g0, g1, g2 + del g0, g1, g2 #删除 - # Scheduler + # 神经网络 学习调度 if opt.linear_lr: - lf = lambda x: (1 - x / (epochs - 1)) * (1.0 - hyp['lrf']) + hyp['lrf'] # linear + lf = lambda x: (1 - x / (epochs - 1)) * (1.0 - hyp['lrf']) + hyp['lrf'] # 计算学习率的线性衰减 else: - lf = one_cycle(1, hyp['lrf'], epochs) # cosine 1->hyp['lrf'] - scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf) # plot_lr_scheduler(optimizer, scheduler, epochs) + lf = one_cycle(1, hyp['lrf'], epochs) # 周期变化 + scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf) - # EMA + # 使用指数移动平均(EMA)来平滑模型权重 ema = ModelEMA(model) if RANK in [-1, 0] else None # Resume @@ -239,7 +232,7 @@ def train(hyp, # 'path/to/hyp.yaml' 或 hyp 字典 callbacks.run('on_pretrain_routine_end') - # DDP mode + # 处理DDP模型 if cuda and RANK != -1: model = DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK) @@ -305,7 +298,7 @@ def train(hyp, # 'path/to/hyp.yaml' 或 hyp 字典 if 'momentum' in x: x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']]) - # Multi-scale + # 判断是否使用多尺度训练 if opt.multi_scale: sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs # size sf = sz / max(imgs.shape[2:]) # scale factor @@ -395,15 +388,9 @@ def train(hyp, # 'path/to/hyp.yaml' 或 hyp 字典 if RANK == -1 and stopper(epoch=epoch, fitness=fi): break - # Stop DDP TODO: known issues shttps://github.com/ultralytics/yolov5/pull/4576 - # stop = stopper(epoch=epoch, fitness=fi) - # if RANK == 0: - # dist.broadcast_object_list([stop], 0) # broadcast 'stop' to all ranks + - # Stop DPP - # with torch_distributed_zero_first(RANK): - # if stop: - # break # must break all DDP ranks + # end epoch ---------------------------------------------------------------------------------------------------- # end training ----------------------------------------------------------------------------------------------------- @@ -526,48 +513,50 @@ def main(opt, callbacks=Callbacks()): LOGGER.info('Destroying process group... ') dist.destroy_process_group() - # Evolve hyperparameters (optional) + # 演化超参数 else: - # Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit) - meta = {'lr0': (1, 1e-5, 1e-1), # initial learning rate (SGD=1E-2, Adam=1E-3) - 'lrf': (1, 0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf) - 'momentum': (0.3, 0.6, 0.98), # SGD momentum/Adam beta1 - 'weight_decay': (1, 0.0, 0.001), # optimizer weight decay - 'warmup_epochs': (1, 0.0, 5.0), # warmup epochs (fractions ok) - 'warmup_momentum': (1, 0.0, 0.95), # warmup initial momentum - 'warmup_bias_lr': (1, 0.0, 0.2), # warmup initial bias lr - 'box': (1, 0.02, 0.2), # box loss gain - 'cls': (1, 0.2, 4.0), # cls loss gain - 'cls_pw': (1, 0.5, 2.0), # cls BCELoss positive_weight - 'obj': (1, 0.2, 4.0), # obj loss gain (scale with pixels) - 'obj_pw': (1, 0.5, 2.0), # obj BCELoss positive_weight - 'iou_t': (0, 0.1, 0.7), # IoU training threshold - 'anchor_t': (1, 2.0, 8.0), # anchor-multiple threshold - 'anchors': (2, 2.0, 10.0), # anchors per output grid (0 to ignore) - 'fl_gamma': (0, 0.0, 2.0), # focal loss gamma (efficientDet default gamma=1.5) - 'hsv_h': (1, 0.0, 0.1), # image HSV-Hue augmentation (fraction) - 'hsv_s': (1, 0.0, 0.9), # image HSV-Saturation augmentation (fraction) - 'hsv_v': (1, 0.0, 0.9), # image HSV-Value augmentation (fraction) - 'degrees': (1, 0.0, 45.0), # image rotation (+/- deg) - 'translate': (1, 0.0, 0.9), # image translation (+/- fraction) - 'scale': (1, 0.0, 0.9), # image scale (+/- gain) - 'shear': (1, 0.0, 10.0), # image shear (+/- deg) - 'perspective': (0, 0.0, 0.001), # image perspective (+/- fraction), range 0-0.001 - 'flipud': (1, 0.0, 1.0), # image flip up-down (probability) - 'fliplr': (0, 0.0, 1.0), # image flip left-right (probability) - 'mosaic': (1, 0.0, 1.0), # image mixup (probability) - 'mixup': (1, 0.0, 1.0), # image mixup (probability) - 'copy_paste': (1, 0.0, 1.0)} # segment copy-paste (probability) + # 超参数演化元数据 + meta = { + 'lr0': (1, 1e-5, 1e-1), # 初始学习率（SGD=0.01, Adam=0.001） + 'lrf': (1, 0.01, 1.0), # 最终OneCycleLR学习率（lr0 * lrf） + 'momentum': (0.3, 0.6, 0.98), # SGD动量/Adam beta1 + 'weight_decay': (1, 0.0, 0.001), # 优化器权重衰减 + 'warmup_epochs': (1, 0.0, 5.0), # 预热epochs（可以接受小数） + 'warmup_momentum': (1, 0.0, 0.95), # 预热初始动量 + 'warmup_bias_lr': (1, 0.0, 0.2), # 预热初始偏置学习率 + 'box': (1, 0.02, 0.2), # 边界框损失增益 + 'cls': (1, 0.2, 4.0), # 类别损失增益 + 'cls_pw': (1, 0.5, 2.0), # 类别BCELoss正样本权重 + 'obj': (1, 0.2, 4.0), # 目标损失增益（随像素缩放） + 'obj_pw': (1, 0.5, 2.0), # 目标BCELoss正样本权重 + 'iou_t': (0, 0.1, 0.7), # IoU训练阈值 + 'anchor_t': (1, 2.0, 8.0), # 锚点多重阈值 + 'anchors': (2, 2.0, 10.0), # 每个输出网格的锚点数（设为0则忽略） + 'fl_gamma': (0, 0.0, 2.0), # 焦点损失gamma（efficientDet默认gamma=1.5） + 'hsv_h': (1, 0.0, 0.1), # 图像HSV-色调增强（比例） + 'hsv_s': (1, 0.0, 0.9), # 图像HSV-饱和度增强（比例） + 'hsv_v': (1, 0.0, 0.9), # 图像HSV-亮度增强（比例） + 'degrees': (1, 0.0, 45.0), # 图像旋转（+/- 度） + 'translate': (1, 0.0, 0.9), # 图像平移（+/- 比例） + 'scale': (1, 0.0, 0.9), # 图像缩放（+/- 增益） + 'shear': (1, 0.0, 10.0), # 图像剪切（+/- 度） + 'perspective': (0, 0.0, 0.001), # 图像透视（+/- 比例）, 范围0-0.001 + 'flipud': (1, 0.0, 1.0), # 图像上下翻转（概率） + 'fliplr': (0, 0.0, 1.0), # 图像左右翻转（概率） + 'mosaic': (1, 0.0, 1.0), # 图像混拼（概率） + 'mixup': (1, 0.0, 1.0), # 图像混合（概率） + 'copy_paste': (1, 0.0, 1.0) # 片段复制粘贴（概率） + } with open(opt.hyp, errors='ignore') as f: - hyp = yaml.safe_load(f) # load hyps dict - if 'anchors' not in hyp: # anchors commented in hyp.yaml + hyp = yaml.safe_load(f) # 加载超参数字典 + if 'anchors' not in hyp: # 设置默认值 hyp['anchors'] = 3 - opt.noval, opt.nosave, save_dir = True, True, Path(opt.save_dir) # only val/save final epoch - # ei = [isinstance(x, (int, float)) for x in hyp.values()] # evolvable indices + opt.noval, opt.nosave, save_dir = True, True, Path(opt.save_dir) + # 路径 evolve_yaml, evolve_csv = save_dir / 'hyp_evolve.yaml', save_dir / 'evolve.csv' if opt.bucket: - os.system(f'gsutil cp gs://{opt.bucket}/evolve.csv {save_dir}') # download evolve.csv if exists + os.system(f'gsutil cp gs://{opt.bucket}/evolve.csv {save_dir}') # 下载evolve.csv for _ in range(opt.evolve): # generations to evolve if evolve_csv.exists(): # if evolve.csv exists: select best hyps and mutate @@ -615,16 +604,14 @@ def main(opt, callbacks=Callbacks()): def run(**kwargs): - # Usage: import train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt') + opt = parse_opt(True) for k, v in kwargs.items(): setattr(opt, k, v) main(opt) -# python train.py --data mask_data.yaml --cfg mask_yolov5s.yaml --weights pretrained/yolov5s.pt --epoch 100 --batch-size 4 --device cpu -# python train.py --data mask_data.yaml --cfg mask_yolov5l.yaml --weights pretrained/yolov5l.pt --epoch 100 --batch-size 4 -# python train.py --data mask_data.yaml --cfg mask_yolov5m.yaml --weights pretrained/yolov5m.pt --epoch 100 --batch-size 4 +# if __name__ == "__main__": opt = parse_opt() main(opt) diff --git a/src/image_recognition/val.py b/src/image_recognition/val.py index 4753eff..5a07aa9 100644 --- a/src/image_recognition/val.py +++ b/src/image_recognition/val.py @@ -1,11 +1,4 @@ -# YOLOv5 🚀 by Ultralytics, GPL-3.0 license -""" -Validate a trained YOLOv5 model accuracy on a custom dataset - -Usage: - $ python path/to/val.py --data coco128.yaml --weights yolov5s.pt --img 640 -""" - +#评估准确性 import argparse import json import os diff --git a/src/image_recognition/window.py b/src/image_recognition/window.py index b7892b4..1567185 100644 --- a/src/image_recognition/window.py +++ b/src/image_recognition/window.py @@ -1,12 +1,5 @@ -# -*- coding: utf-8 -*- """ -------------------------------------------------- -Project Name: yolov5-jungong -File Name: window.py.py -Author: chenming -Create Date: 2021/11/8 -Description：图形化界面，可以检测摄像头、视频和图片文件 -------------------------------------------------- +图形化界面 """ # 设置tmp的目录来放中间的处理结果 import shutil