打标签制作自己的数据集并在TensorFlow框架上训练

标签工具labelImg

用labelimg对自己的数据做好标注，只有一类预测桃子图像。
注释文件保存为xml格式，满足PASCAL VOC风格,如下图1把图片和标签放在一个文件夹内（data）

转换数据格式，可以在tensorflow框架下读取

需将标记完的数据集xml的文件转换为TFRecord格式的文件
1、先转换为csv格式
转换代码为：

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,
                     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('D:/programs/models-master/research/object_detection/data/train_peaches.csv', index=None)
    eval_df.to_csv('D:/programs/models-master/research/object_detection/data/eval_peaches.csv', index=None)

def main():
    path = 'D:/dataset/data'
    xml_to_csv(path)
    print('Successfully converted xml to csv.')
main()

2、再转换为TFRecord格式
转换代码为：

from __future__ import division
from __future__ import print_function
from __future__ import absolute_import

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 == 'peach':
        return 1
    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.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 = 'D:/dataset/data'
    
    # 生成train.record文件
    output_path = 'D:/programs/models-master/research/object_detection/data/train_peaches.record'
    csv_input = 'D:/programs/models-master/research/object_detection/data/train_peaches.csv'
    main(csv_input, output_path, imgPath)

    # 生成验证文件 eval.record
    output_path = 'D:/programs/models-master/research/object_detection/data/eval_peaches.record'
    csv_input = 'D:/programs/models-master/research/object_detection/data/eval_peaches.csv'
    main(csv_input, output_path, imgPath)

运行结果

如下图：

训练自己的数据集

结果如图



参考博客：
https://blog.csdn.net/RobinTomps/article/details/78115628?locationNum=5&fps=1