可以在云盘下载打包文件包括API,数据
把原有的文件夹下面的object_detection删掉,这里面的(__init____.py)文件百度云盘上传不了,全都没成功,所以在把文件下来之后object_detection/object_detection/下的内容删掉,把object_detection.zip解压到object_detection里面。
首先先下载图片
网友ACLJW的爬虫代码简单高效
pachong.py
# @File : pachong.py
import requests
import re
import os
from pypinyin import pinyin, lazy_pinyin
def getHTMLText(url):
try:
r = requests.get(url,timeout=30)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
print("")
def getPageUrls(text,name):
re_pageUrl=r'href="(.+)">\s*<img src="(.+)" alt="'+name
return re.findall(re_pageUrl,text)
def downPictures(text,root,name,L):
pageUrls=getPageUrls(text,name)
titles=re.findall(r'alt="'+name+r'(.+)" ',text)
for i in range(len(pageUrls)):
pageUrl=pageUrls[i][0]
path = root + titles[i]+ "//"
if not os.path.exists(path):
os.mkdir(path)
if not os.listdir(path):
pageText=getHTMLText(pageUrl)
totalPics=int(re.findall(r'<em>(.+)</em>)',pageText)[0])
downUrl=re.findall(r'href="(.+?)" class="">下载图片',pageText)[0]
cnt=1;
while(cnt<=totalPics):
L += 1
picPath=path+"%s.jpg"%str(L)
r=requests.get(downUrl)
with open(picPath,'wb') as f:
f.write(r.content)
f.close()
print('{} - 第{}张下载已完成\n'.format(titles[i],L))
cnt+=1
nextPageUrl=re.findall(r'href="(.+?)">下一张',pageText)[0]
pageText=getHTMLText(nextPageUrl)
downUrl=re.findall(r'href="(.+?)" class="">下载图片',pageText)[0]
return L
def main():
name=input("请输入你喜欢的明星的名字:")
nameUrl="http://www.win4000.com/mt/"+''.join(lazy_pinyin(name))+".html"
L = 0
try:
text=getHTMLText(nameUrl)
if not re.findall(r'暂无(.+)!',text):
root = "C:/Users/yanghe/Desktop/data/"+name+"//"
if not os.path.exists(root):
os.mkdir(root)
L = downPictures(text,root,name, L)
try:
nextPage=re.findall(r'next" href="(.+)"',text)[0]
while(nextPage):
nextText=getHTMLText(nextPage)
L = downPictures(nextText,root,name,L)
nextPage=re.findall(r'next" href="(.+)"',nextText)[0]
except IndexError:
print("已全部下载完毕")
except TypeError:
print("不好意思,没有{}的照片".format(name))
return
if __name__ == '__main__':
main()
打上标签
1.打标签用的软件是是labelImg.exe,这款软件操作简单。
labelImg.exe的快捷键
2.这里需要设置类别:
这里有一个open_dir是照片文件打开的目录,还有一个Ctrl+R更改默认xml文件地址。这里是为了生成和Pascal voc2007数据集一样格式的文件。
每打一张图片就保存一下,点下ok就行了,好像是自动保存的,超级简单。
给戚薇打上标签
图片爬到的质量有问题,大部分是侧脸,柳岩的全是戴帽子的照片,哎!!这明星的写真集照片看的眼都花了
Pascal voc2007数据集简单介绍
具体细节查看点这里:数据集:Pascal voc2007数据集分析
labelImg
在Pascal voc2007中(对于2007_000392.jpg)对于这张图有如下的对应xml文件。(2007_000392.jpg图在下面)
#2007_000392.xml
<annotation>
<folder>VOC2012</folder>
<filename>2007_000392.jpg</filename> //文件名
<source> //图像来源(不重要)
<database>The VOC2007 Database</database>
<annotation>PASCAL VOC2007</annotation>
<image>flickr</image>
</source>
<size> //图像尺寸(长宽以及通道数)
<width>500</width>
<height>332</height>
<depth>3</depth>
</size>
<segmented>1</segmented> //是否用于分割(在图像物体识别中01无所谓)
<object> //检测到的物体
<name>horse</name> //物体类别
<pose>Right</pose> //拍摄角度
<truncated>0</truncated> //是否被截断(0表示完整)
<difficult>0</difficult> //目标是否难以识别(0表示容易识别)
<bndbox> //bounding-box(包含左下角和右上角xy坐标)
<xmin>100</xmin>
<ymin>96</ymin>
<xmax>355</xmax>
<ymax>324</ymax>
</bndbox>
</object>
<object> //检测到多个物体
<name>person</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>198</xmin>
<ymin>58</ymin>
<xmax>286</xmax>
<ymax>197</ymax>
</bndbox>
</object>
</annotation>
在2007_000392.jpg这张图里面有个人在骑马。在xml文件里面object有两个(person和horse),包括信息有是否识别困难,截断,角度等,左下角和右上角的坐标。
2007_000392.jpg
我的类别如下:
把xml文件生成csv文件
这里的path 就是保存xml文件的目录,data是你要保存csv文件的目录。
具体查看请点这里:TensorFlow Object Detection API教程——利用自己制作的数据集进行训练预测和测试
这里记得设置一下你的训练集和测试集的大小,这里是0.67
# -*- coding: utf-8 -*-
import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET
def xml_to_csv(path):
xml_list = []
# 读取注释文件
for xml_file in glob.glob(path + '/*.xml'):
tree = ET.parse(xml_file)
root = tree.getroot()
for member in root.findall('object'):
value = (root.find('filename').text + '.jpg',
int(root.find('size')[0].text),
int(root.find('size')[1].text),
member[0].text,
int(member[4][0].text),
int(member[4][1].text),
int(member[4][2].text),
int(member[4][3].text)
)
xml_list.append(value)
column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']
# 将所有数据分为样本集和验证集,一般按照3:1的比例
train_list = xml_list[0: int(len(xml_list) * 0.67)]
eval_list = xml_list[int(len(xml_list) * 0.67) + 1: ]
# 保存为CSV格式
train_df = pd.DataFrame(train_list, columns=column_name)
eval_df = pd.DataFrame(eval_list, columns=column_name)
train_df.to_csv('data/train.csv', index=None)
eval_df.to_csv('data/eval.csv', index=None)
def main():
path = './xml'
xml_to_csv(path)
print('Successfully converted xml to csv.')
main()
把csv生成TFrecord文件
import os
import io
import pandas as pd
import tensorflow as tf
from PIL import Image
from object_detection.utils import dataset_util
from collections import namedtuple, OrderedDict
flags = tf.app.flags
flags.DEFINE_string('csv_input', '', 'Path to the CSV input')
flags.DEFINE_string('output_path', '', 'Path to output TFRecord')
FLAGS = flags.FLAGS
# 将分类名称转成ID号
def class_text_to_int(row_label):
if row_label == 'damimi':
return 1
elif row_label == 'fanbingbing':
return 2
elif row_label == 'liuyan':
return 3
elif row_label == 'nazha':
return 4
elif row_label == 'xiaowei':
return 5
else:
print('NONE: ' + row_label)
None
def split(df, group):
data = namedtuple('data', ['filename', 'object'])
gb = df.groupby(group)
return [data(filename, gb.get_group(x)) for filename, x in zip(gb.groups.keys(), gb.groups)]
def create_tf_example(group, path):
print(os.path.join(path, '{}'.format(group.filename)))
with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)), 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = Image.open(encoded_jpg_io)
width, height = image.size
filename = (group.filename + '.jpg').encode('utf8')
image_format = b'jpg'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
for index, row in group.object.iterrows():
xmins.append(row['xmin'] / width)
xmaxs.append(row['xmax'] / width)
ymins.append(row['ymin'] / height)
ymaxs.append(row['ymax'] / height)
classes_text.append(row['class'].encode('utf8'))
classes.append(class_text_to_int(row['class']))
tf_example = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(filename),
'image/source_id': dataset_util.bytes_feature(filename),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
}))
return tf_example
def main(csv_input, output_path, imgPath):
writer = tf.python_io.TFRecordWriter(output_path)
path = imgPath
examples = pd.read_csv(csv_input)
grouped = split(examples, 'filename')
for group in grouped:
tf_example = create_tf_example(group, path)
writer.write(tf_example.SerializeToString())
writer.close()
print('Successfully created the TFRecords: {}'.format(output_path))
if __name__ == '__main__':
imgPath = './xml' #你的图片路径
# 生成train.record文件
output_path = 'data/train.record' #你的record保存路径
csv_input = 'data/train.csv' #你的csv文件路径
main(csv_input, output_path, imgPath)
# 生成验证文件 eval.record
output_path = 'data/eval.record'
csv_input = 'data/eval.csv'
main(csv_input, output_path, imgPath)
设置一下图片路径和record的保存路径就行了
修改ssd_inception_v2_coco.config文件
就是修改一下目录,训练次数,record文件,和lable文件等信息:
num_classes: 5
num_steps: 10000
batch_size: 20
fine_tune_checkpoint:"ssd_inception_v2_coco_2018_01_28/model.ckpt"
train_input_reader:的下面{
input_path: "record/train.record"
label_map_path: "record/label_map.pbtxt"}
test_input_reader:的下面{
input_path: "record/val.record"
label_map_path: "record/label_map.pbtxt"}
# SSD with Inception v2 configuration for MSCOCO Dataset.
# Users should configure the fine_tune_checkpoint field in the train config as
# well as the label_map_path and input_path fields in the train_input_reader and
# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
# should be configured.
model {
ssd {
num_classes: 5
box_coder {
faster_rcnn_box_coder {
y_scale: 10.0
x_scale: 10.0
height_scale: 5.0
width_scale: 5.0
}
}
matcher {
argmax_matcher {
matched_threshold: 0.5
unmatched_threshold: 0.5
ignore_thresholds: false
negatives_lower_than_unmatched: true
force_match_for_each_row: true
}
}
similarity_calculator {
iou_similarity {
}
}
anchor_generator {
ssd_anchor_generator {
num_layers: 6
min_scale: 0.2
max_scale: 0.95
aspect_ratios: 1.0
aspect_ratios: 2.0
aspect_ratios: 0.5
aspect_ratios: 3.0
aspect_ratios: 0.3333
reduce_boxes_in_lowest_layer: true
}
}
image_resizer {
fixed_shape_resizer {
height: 300
width: 300
}
}
box_predictor {
convolutional_box_predictor {
min_depth: 0
max_depth: 0
num_layers_before_predictor: 0
use_dropout: false
dropout_keep_probability: 0.8
kernel_size: 3
box_code_size: 4
apply_sigmoid_to_scores: false
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
}
}
}
feature_extractor {
type: 'ssd_inception_v2'
min_depth: 16
depth_multiplier: 1.0
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,
scale: true,
center: true,
decay: 0.9997,
epsilon: 0.001,
}
}
}
loss {
classification_loss {
weighted_sigmoid {
anchorwise_output: true
}
}
localization_loss {
weighted_smooth_l1 {
anchorwise_output: true
}
}
hard_example_miner {
num_hard_examples: 3000
iou_threshold: 0.99
loss_type: CLASSIFICATION
max_negatives_per_positive: 3
min_negatives_per_image: 0
}
classification_weight: 1.0
localization_weight: 1.0
}
normalize_loss_by_num_matches: true
post_processing {
batch_non_max_suppression {
score_threshold: 1e-8
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 100
}
score_converter: SIGMOID
}
}
}
train_config: {
batch_size: 20
optimizer {
rms_prop_optimizer: {
learning_rate: {
exponential_decay_learning_rate {
initial_learning_rate: 0.004
decay_steps: 10000
decay_factor: 0.95
}
}
momentum_optimizer_value: 0.9
decay: 0.9
epsilon: 1.0
}
}
fine_tune_checkpoint: "ssd_inception_v2_coco_2018_01_28/model.ckpt"
from_detection_checkpoint: true
# Note: The below line limits the training process to 200K steps, which we
# empirically found to be sufficient enough to train the pets dataset. This
# effectively bypasses the learning rate schedule (the learning rate will
# never decay). Remove the below line to train indefinitely.
num_steps: 1000
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
ssd_random_crop {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "record/train.record"
}
label_map_path: "record/label_map.pbtxt"
}
eval_config: {
num_examples: 4952
# Note: The below line limits the evaluation process to 10 evaluations.
# Remove the below line to evaluate indefinitely.
max_evals: 10
}
eval_input_reader: {
tf_record_input_reader {
input_path: "record/val.record"
}
label_map_path: "record/label_map.pbtxt"
shuffle: false
num_readers: 1
num_epochs: 1
}
训练
这是我的目录图
在cmd下执行,cpu训练一个晚上才666次,这个精度不咋滴。
python train.py \
--logtostderr \
--train_dir=train \
--pipeline_config_path=ssd_inception_v2_coco.config
生成pb文件
训练666次了。早上起来直接Ctrl+c关掉,如果想继续在666上继续训练,直接执行上面的就可以了,它会读取train 下面的训练文件的。
python export_inference_graph.py
--pipeline_config_path ssd_inception_v2_coco.config
--trained_checkpoint_prefix "pb/model.ckpt-666"
--output_directory pb
生成pb的时候出错了
ValueError: Protocol message RewriterConfig has no "layout_optimizer" field
在/object_detection/exporter.py”文件,将第72行的layout_optimizer与相互更改optimize_tensor_layout就解决问题啦。
测试
test_image.py
import matplotlib.pyplot as plt
import numpy as np
import os
import tensorflow as tf
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
from PIL import Image
def test():
#重置图
tf.reset_default_graph()
'''
载入模型以及数据集样本标签,加载待测试的图片文件
'''
#指定要使用的模型的路径 包含图结构,以及参数
PATH_TO_CKPT = 'pb/frozen_inference_graph.pb'
#测试图片所在的路径
PATH_TO_TEST_IMAGES_DIR = './test_images'
TEST_IMAGE_PATHS = [os.path.join(PATH_TO_TEST_IMAGES_DIR,'{}.jpg'.format(i)) for i in range(1,11) ]
#数据集对应的label pascal_label_map.pbtxt文件保存了index和类别名之间的映射
PATH_TO_LABELS = "record/label_map.pbtxt"
NUM_CLASSES = 5
#重新定义一个图
output_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT,'rb') as fid:
#将*.pb文件读入serialized_graph
serialized_graph = fid.read()
#将serialized_graph的内容恢复到图中
output_graph_def.ParseFromString(serialized_graph)
#print(output_graph_def)
#将output_graph_def导入当前默认图中(加载模型)
tf.import_graph_def(output_graph_def,name='')
print('模型加载完成')
#载入coco数据集标签文件
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map,max_num_classes = NUM_CLASSES,use_display_name = True)
category_index = label_map_util.create_category_index(categories)
'''
定义session
'''
def load_image_into_numpy_array(image):
'''
将图片转换为ndarray数组的形式
'''
im_width,im_height = image.size
return np.array(image.getdata()).reshape((im_height,im_width,3)).astype(np.uint0)
#设置输出图片的大小
IMAGE_SIZE = (12,8)
#使用默认图,此时已经加载了模型
detection_graph = tf.get_default_graph()
with tf.Session(graph=detection_graph) as sess:
for image_path in TEST_IMAGE_PATHS:
image = Image.open(image_path)
#将图片转换为numpy格式
image_np = load_image_into_numpy_array(image)
'''
定义节点,运行并可视化
'''
#将图片扩展一维,最后进入神经网络的图片格式应该是[1,?,?,3]
image_np_expanded = np.expand_dims(image_np,axis = 0)
'''
获取模型中的tensor
'''
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
#boxes用来显示识别结果
boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
#Echo score代表识别出的物体与标签匹配的相似程度,在类型标签后面
scores = detection_graph.get_tensor_by_name('detection_scores:0')
classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
#开始检查
boxes,scores,classes,num_detections = sess.run([boxes,scores,classes,num_detections],
feed_dict={image_tensor:image_np_expanded})
#可视化结果
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8)
plt.figure(figsize=IMAGE_SIZE)
print(type(image_np))
print(image_np.shape)
image_np = np.array(image_np,dtype=np.uint8)
plt.imshow(image_np)
plt.show()
if __name__ == '__main__':
test()
如下执行结果:
范冰冰
这是大咪咪
其他人的识别都不是很高,可能和训练图片有关
小礼物走一走,来简书关注我