You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
134 lines
2.7 KiB
134 lines
2.7 KiB
#!/usr/bin/env python
|
|
# coding: utf-8
|
|
|
|
# 数据集：
|
|
# /data/shixunfiles/26a2e3c3b2c50fe54e2fcab6e031a141_1607408726958.zip
|
|
|
|
# ## 垃圾检测练习题——车辆检测
|
|
|
|
# In[1]:
|
|
|
|
|
|
get_ipython().system('pip install paddlehub==1.8.1 -i https://pypi.tuna.tsinghua.edu.cn/simple')
|
|
|
|
|
|
# In[2]:
|
|
|
|
|
|
import paddlehub as hub
|
|
|
|
|
|
# In[4]:
|
|
|
|
|
|
module = hub.Module(name="mobilenet_v2_imagenet")
|
|
|
|
|
|
# In[5]:
|
|
|
|
|
|
get_ipython().system('unzip -o /data/shixunfiles/26a2e3c3b2c50fe54e2fcab6e031a141_1607408726958.zip')
|
|
|
|
|
|
# In[22]:
|
|
|
|
|
|
from paddlehub.dataset.base_cv_dataset import BaseCVDataset
|
|
|
|
class DemoDataset(BaseCVDataset):
|
|
def __init__(self):
|
|
# 数据集存放位置
|
|
self.dataset_dir = "car_datasets/"
|
|
super(DemoDataset, self).__init__(
|
|
base_path=self.dataset_dir,
|
|
train_list_file="train_list.txt",
|
|
validate_list_file="validate_list.txt",
|
|
test_list_file="test_list.txt",
|
|
label_list=["bus","jeep","suv","truck"]
|
|
)
|
|
dataset = DemoDataset()
|
|
|
|
|
|
# In[23]:
|
|
|
|
|
|
data_reader = hub.reader.ImageClassificationReader(
|
|
image_width=module.get_expected_image_width(),
|
|
image_height=module.get_expected_image_height(),
|
|
images_mean=module.get_pretrained_images_mean(),
|
|
images_std=module.get_pretrained_images_std(),
|
|
dataset=dataset)
|
|
|
|
|
|
# In[26]:
|
|
|
|
|
|
config = hub.RunConfig(
|
|
use_cuda=True,
|
|
num_epoch=10,
|
|
# checkpoint_dir="cv_finetune_turtorial_demo",
|
|
batch_size=32,
|
|
eval_interval=50,
|
|
strategy=hub.finetune.strategy.DefaultFinetuneStrategy())
|
|
|
|
|
|
# In[25]:
|
|
|
|
|
|
input_dict, output_dict, program = module.context(trainable=True)
|
|
|
|
img = input_dict["image"]
|
|
|
|
feature_map = output_dict["feature_map"]
|
|
|
|
feed_list = [img.name]
|
|
|
|
task = hub.ImageClassifierTask(
|
|
data_reader=data_reader,
|
|
feed_list=feed_list,
|
|
feature=feature_map,
|
|
num_classes=dataset.num_labels,
|
|
# num_classes=3,
|
|
config=config)
|
|
|
|
|
|
# In[27]:
|
|
|
|
|
|
run_states = task.finetune_and_eval()
|
|
|
|
|
|
# In[29]:
|
|
|
|
|
|
import numpy as np
|
|
import matplotlib.pyplot as plt
|
|
import pandas as pd
|
|
from pandas import Series,DataFrame
|
|
get_ipython().run_line_magic('matplotlib', 'inline')
|
|
|
|
data = ["car_datasets/test/suv/suv_4.jpg"]
|
|
label_map = dataset.label_dict()
|
|
index = 0
|
|
# get classification result
|
|
run_states = task.predict(data=data)
|
|
results = [run_state.run_results for run_state in run_states]
|
|
|
|
for batch_result in results:
|
|
# get predict index
|
|
batch_result = np.argmax(batch_result, axis=2)[0]
|
|
for result in batch_result:
|
|
index += 1
|
|
result = label_map[result]
|
|
print("input %i is %s, and the predict result is ( %s )" %
|
|
(index, data[index - 1], result))
|
|
d=plt.imread("car_datasets/test/suv/suv_4.jpg")
|
|
plt.imshow(d)
|
|
|
|
|
|
# In[ ]:
|
|
|
|
|
|
|
|
|