记录Tensorflow models的那些坑

以下都是在windows 10环境下进行安装编译

tf models最麻烦的地方就是要安装对应版本的python
而 git上的教程都很老了，安装tensorflow总是会出现各种问题
现在tf 2.x 版本 需要python3.5在以上

tensorflow models 官方安装教程

tensorflow models
下载最新的tf models，链接教程里面有源码连接

Anaconda版本:

Anaconda3-2020.02-Windows-x86_64.exe

安装完anaconda 后
要以 管理员身份运行

创建环境
conda create -n tensorflow1 pip python=3.8

网络不行的时候创建虚拟环境都会失败
自行在网上查找 anaconda 替换源 或者 添加代理的方法
C:\Users\xxx 下有个 .condarc 文件是anaconda的config文件

激活环境
conda activate tensorflow1

在**.condarc**目录下创建pip文件夹，里面创建pip.ini替换pip源

pip.ini 文件内容

[global]
index-url=https://pypi.doubanio.com/simple/
[install]  
trusted-host=pypi.douban.com
disable-pip-version-check = true  
timeout = 6000

这里替换的是豆瓣源 可以在网上查找其他源

然后就是按照官方教程
安装tensorflow
安装完tensorflow后开始编译tf models
按照官方的教程
在models\research路径下运行
python setup.py build
python setup.py install
最新的源码这个路径是没setup.py的，这个文件被藏在其他地方了
直接搜索然后拉到这个目录下就行了

如果install的时候提示某些包版本过高或者过低，运行
pip install a==b
a表示某个包
b表示对应的版本

如果最终提示了tensorflow版本过低
表示 ts models的源码版本过高了，找低版本的就行了

编译完后
官方教程运行 object_detection_tutorial.ipynb
这个文件也被藏起来了
直接搜索拖到当前目录下就好了

然后创建个新的虚拟环境
pip install labelimg
labelimg
运行这个软件
对图片进行标记

按照官网教程在object_detection下创建images/train 和 images/test文件夹

按照官网教程运行两个脚本
不用去下那两个脚本了
没用
直接贴代码

xml_to_csv.py

import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET


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,
                     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']
    xml_df = pd.DataFrame(xml_list, columns=column_name)
    return xml_df


def main():
    # train xml to csv
    cwd_path = os.getcwd();
    print('cwd path: %s' % (cwd_path))

    image_path = cwd_path + '\\images\\train'
    print('xml path:%s' % (image_path))
    xml_df = xml_to_csv(image_path)
    xml_df.to_csv(cwd_path + '\\images\\train_labels.csv', index=None)

    # test xml to csv
    image_path = cwd_path + '\\images\\test'
    print('xml path:%s' % (image_path))
    xml_df = xml_to_csv(image_path)
    xml_df.to_csv(cwd_path + '\\images\\test_labels.csv', index=None)

    # finished
    print('Successfully converted xml to csv.')


main()

generate_tfrecord.py

"""
Usage:
  # From tensorflow/models/
  # Create train data:
  python generate_tfrecord.py --csv_input=data/train_labels.csv  --output_path=train.record
  # Create test data:
  python generate_tfrecord.py --csv_input=data/test_labels.csv  --output_path=test.record
"""
from __future__ import division
from __future__ import print_function
from __future__ import absolute_import

import os
import io
import pandas as pd
import tensorflow.compat.v1 as tf

#from absl import app
#from absl import flags

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.DEFINE_string('image_dir', '', 'Path to images')
FLAGS = flags.FLAGS


# TO-DO replace this with label map
def class_text_to_int(row_label):
    if row_label == 'person':
        return 1
    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.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': 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(_):
    writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
    path = os.path.join(FLAGS.image_dir)
    examples = pd.read_csv(FLAGS.csv_input)
    grouped = split(examples, 'filename')
    for group in grouped:
        tf_example = create_tf_example(group, path)
        writer.write(tf_example.SerializeToString())

    writer.close()
    output_path = os.path.join(os.getcwd(), FLAGS.output_path)
    print('Successfully created the TFRecords: {}'.format(output_path))


if __name__ == '__main__':
    tf.app.run()

按照官网教程将图片和 xml 放入对应的文件夹
将脚本放在research\object_detection 下运行这两个脚本就行了

会生成 test.record 和 train.record

问题

1. ImportError: cannot import name ‘center_net_pb2’ from 'object_detection.protos’
   （返回到research\目录下运行 protoc --python_out=. .\object_detection\protos\center_net.proto 然后在python setup.py build 和 python setup.py install）