1.使用labelimg工具
打开
进入自己使用的虚拟环境
activate name#自己的环境名字
然后直接pip,不用看网上其他的什么zip安装麻烦的不行还报错,参考:(1条消息) labelImg使用教程_G果的博客-CSDN博客_labelimg)
pip insatll labelimg
pip好后,直接命令行输入lanelimg打开工具
labelimg
open打开单个img图像文件,open Dir打开图像文件夹,
注意的是:ctrl+s保存后输入你的标签分类名字,后面转换为ecord文件会用到该名字标签映射!
不然会提示报错
2.xml转换为csv文件
xml_to_cvs.py
注意:文件路径!!
import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET
os.chdir('D:\\AAAAA\\tf5_img\\TEST')#保存路径
path = 'D:\\AAAAA\\tf5_img\\TEST'#xnl文件路径
def xml_to_csv(path):
xml_list = []
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,
float(root.find('size')[0].text),
float(root.find('size')[1].text),
member[0].text,
float(member[4][0].text),
float(member[4][1].text),
float(member[4][2].text),
float(member[4][3].text)
)
xml_list.append(value)
column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']
xml_df = pd.DataFrame(xml_list, columns=column_name)
return xml_df
def main():
image_path = path
xml_df = xml_to_csv(image_path)
xml_df.to_csv('pedestrian_headshoulder.csv', index=None)
print('Successfully converted xml to csv.')
main()
3.cvs转换为recoed文件
由于github原作者(datitran/raccoon_dataset: The dataset is used to train my own raccoon detector and I blogged about it on Medium (github.com))为tensorflow1.X版本原因会报app、v1等bug,其他bug可自行搜索
很多博主解决方法是引入.compat.v1模块,但是现在版本已经移除了compat模块,无法解决该问题。
注意:路径问题!!!
注意:cvs文件改为utf-8编码!
generate_tfrecord.py修改源码为:(参考哪的找不到了)
from __future__ import division
from __future__ import print_function
from __future__ import absolute_import
import os
import io
import pandas as pd
from PIL import Image
from collections import namedtuple
import tensorflow as tf
# CSV文件的位置
csv_input = 'D:\\AAAAA\\tf5_img/TEST\\pedestrian_headshoulder.csv'
# TFRecords的输出位置及文件名
output_path = 'D:\\AAAAA\\tf5_img\\TEST\\img_train.record'
# 图像数据的位置及文件名
image_dir = 'D:\\AAAAA\\tf5_img\\TEST'
def class_text_to_int(row_label):
if row_label == 'LiveLong':
return 0
else:
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):
with tf.io.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.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': tf.train.Feature(int64_list=tf.train.Int64List(value=[height])),
'image/width': tf.train.Feature(int64_list=tf.train.Int64List(value=[width])),
'image/filename': tf.train.Feature(bytes_list=tf.train.BytesList(value=[filename])),
'image/source_id': tf.train.Feature(bytes_list=tf.train.BytesList(value=[filename])),
'image/encoded': tf.train.Feature(bytes_list=tf.train.BytesList(value=[encoded_jpg])),
'image/format': tf.train.Feature(bytes_list=tf.train.BytesList(value=[image_format])),
'image/object/bbox/xmin': tf.train.Feature(float_list=tf.train.FloatList(value=xmins)),
'image/object/bbox/xmax': tf.train.Feature(float_list=tf.train.FloatList(value=xmaxs)),
'image/object/bbox/ymin': tf.train.Feature(float_list=tf.train.FloatList(value=ymins)),
'image/object/bbox/ymax': tf.train.Feature(float_list=tf.train.FloatList(value=ymaxs)),
'image/object/class/text': tf.train.Feature(bytes_list=tf.train.BytesList(value=classes_text)),
'image/object/class/label': tf.train.Feature(int64_list=tf.train.Int64List(value=classes)),
}))
return tf_example
def main():
writer = tf.io.TFRecordWriter(output_path)
path = os.path.join(os.getcwd(), image_dir)
examples = pd.read_csv(csv_input,encoding='gbk')
grouped = split(examples, 'filename')
for group in grouped:
tf_example = create_tf_example(group, path)
writer.write(tf_example.SerializeToString())
writer.close()
if __name__ == '__main__':
main()
如果报bug:
是因为标签映射错误,注意自己保存标签的名字。
def class_text_to_int(row_label):
if row_label == 'LiveLong':#自己labelimg保存标签时的名字,有几类分几类
return 0
else:
None
可能还是报utf-8问题bug:
我是通过在读取cvs文件时加上encoding解决:
examples = pd.read_csv(csv_input,encoding='gbk')
关于其他utf-8的bug可参考((2条消息) 执行python generate_tfrecord.py 出现 utf-8‘ codec can‘t decode_Navy的博客-CSDN博客)
如果还是不能成功运行就新建环境安装tensorflow1.x版本运行原github作者code
最后终于成功运行生成record文件