(Ubuntu)Tensorflow object detection API——（3）创建训练/测试数据集

版权声明：转载请注明出处 https://blog.csdn.net/qq_34213260/article/details/85253553

1、下载labelImg工具进行标注

https://github.com/tzutalin/labelImg

（1）点击打开训练图片所在的文件夹

（2）点击框选自己要识别的目标

（3）添加标签并保存，获得同名的xml文件，如图。

2、将文件夹内的xml文件内的信息统一记录到.csv表格中

# Author Qian Chenglong

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

path = 'F:\\2019视觉培训内容\\armor_date' #数据所在的文件夹路径
os.chdir(path)  #改变当前工作目录到指定的路径。
output_name='armor_train.csv' #输出的文件名


def xml_to_csv(path):
    xml_list = []
    for xml_file in glob.glob(path + '/*.xml'): #遍历文件夹下的所有xml文件
        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():
    image_path = path
    xml_df = xml_to_csv(image_path)
    xml_df.to_csv(output_name, index=None)
    print('Successfully converted xml to csv.')


main()

3、由CSV文件生成TFRecord文件

(1)将生成的csv文件移动到F:\models-master\research\object_detection\data文件夹下

（2）写如下.py文件保存为generate_tfrecord.py保存到F:\models-master\research\object_detection路径

# Author Qian Chenglong

"""
Usage:
  # From tensorflow/models/
  # Create train data:
  python generate_tfrecord.py --csv_input=data/tv_vehicle_labels.csv  --output_path=train.record
  # Create test data:
  python generate_tfrecord.py --csv_input=data/test_labels.csv  --output_path=test.record
"""

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

os.chdir('F:\\models-master\\research\\object_detection')  #填写models\\research\\object_detection\\的绝对路径

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


# TO-DO replace this with label map
# 注意将对应的label改成自己的类别！！！！！！！！！！
def class_text_to_int(row_label):
    if row_label == 'armor':       #自己的类别名
        return 1                   #返回的序号，必须不同
    # elif row_label == 'vehicle':
    #     return 2
    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(os.getcwd(), 'images')
    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()

转到F:\models-master\research\object_detection路径：运行如下语句

python generate_tfrecord.py --csv_input=data/armor_train.csv  --output_path=train.record  

#输入文件名和输出文件名根据自己需求修改