将xml格式数据转化为record格式

在使用tensorflow做目标检测时，通过labelimg标注的数据为xml格式的labels，需要将其转化成record格式的文件，才能在tensorflow框架下训练。
该教程主要介绍从将xml格式转化成record格式的方法。

• 需要2个python文件，分别为xml_to_csv.py和generate_tfrecord.py。
• xml_to_csv.py

# xml_to_csv.py
# -*- coding: utf-8 -*-
 
import os, sys
import glob
import pandas as pd
import xml.etree.ElementTree as ET
def xml_to_csv(_path, _out_file):
    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)
    xml_df.to_csv(_out_file, index=None)
    print('Successfully converted xml to csv.')
 
if __name__ == '__main__':
    # convert
    xml_to_csv(sys.argv[1], sys.argv[2])

• generate_tfrecord.py

# generate_tfrecord.py
# -*- coding: utf-8 -*-
 
"""
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
"""
import os
import io
import pandas as pd
import tensorflow as tf
 
from PIL import Image
from object_detection.utils import dataset_util
 
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
 
# 需要修改类别标签
def class_text_to_int(row_label):
    if row_label == 'person':
        return 1
    else:
        None
 
def create_tf_example(row):
    #full_path = os.path.join(os.getcwd(), 'images', '{}'.format(row['filename']))
    full_path = os.path.join(os.path.dirname(FLAGS.csv_input), 'images', '{}'.format(row['filename']))
    with tf.gfile.GFile(full_path, '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 = row['filename'].encode('utf8')
    image_format = b'jpg'
    xmins = [row['xmin'] / width]
    xmaxs = [row['xmax'] / width]
    ymins = [row['ymin'] / height]
    ymaxs = [row['ymax'] / height]
    classes_text = [row['class'].encode('utf8')]
    classes = [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)
    examples = pd.read_csv(FLAGS.csv_input)
    for index, row in examples.iterrows():
        tf_example = create_tf_example(row)
        writer.write(tf_example.SerializeToString())
    writer.close()
 
if __name__ == '__main__':
    tf.app.run()

• 在终端运行如下指令

python xml_to_csv.py /path/to/train ./data/train_labels.csv
python xml_to_csv.py /path/to/test ./data/test_labels.csv

python generate_tfrecord.py --csv_input=data/train_labels.csv  --output_path=train.record
python generate_tfrecord.py --csv_input=data/test_labels.csv  --output_path=test.record

运行后可得到train.record和test.record两个文件。