使用generate_tfrecord.py转换TFRecord时遇UTF-8解码错误求助

将LabelImg生成的XML文件转换为CSV后，进一步转TFRecord文件时，始终出现UnicodeDecodeError，尝试过修改编码（如latin-1）、引入Unidecode库、在Google Colab运行等方法，均无法解决。

运行代码 #

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 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 == 'raccoon':
        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()

错误栈信息 #

Traceback (most recent call last):
  File "C:\Users\user\Downloads\custom object\generate_tfrecord.py", line 91, in <module>
    tf.app.run()
  File "C:\Users\user\AppData\Local\Programs\Python\Python39\lib\site-packages\tensorflow\python\platform\app.py", line 36, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "C:\Users\user\AppData\Local\Programs\Python\Python39\lib\site-packages\absl\app.py", line 308, in run
    _run_main(main, args)
  File "C:\Users\user\AppData\Local\Programs\Python\Python39\lib\site-packages\absl\app.py", line 254, in _run_main
    sys.exit(main(argv))
  File "C:\Users\user\Downloads\custom object\generate_tfrecord.py", line 77, in main
    writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
  File "C:\Users\user\AppData\Local\Programs\Python\Python39\lib\site-packages\tensorflow\python\lib\io\tf_record.py", line 294, in __init__
    super(TFRecordWriter, self).__init__(
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xfd in position 48: invalid start byte

解决方案 #

1. 修正输出路径的字符问题 #

错误触发在TFRecordWriter初始化阶段，说明输出路径包含非UTF-8编码的字符（比如中文、空格、特殊符号）。

• 把路径改成纯英文格式，例如将C:\Users\user\Downloads\custom object\改为C:\Users\user\Downloads\custom_object\，避免空格和非ASCII字符。
• 直接传入不含特殊字符的绝对路径字符串，替代FLAGS参数。

2. 修复class_text_to_int函数的返回值 #

原函数else分支返回None，会导致后续生成TFExample时出现数据类型错误，改为返回默认类别值：

def class_text_to_int(row_label):
    if row_label == 'raccoon':
        return 1
    else:
        return 0  # 替换原有的None，0代表未知类别

3. 指定CSV文件的读取编码 #

如果CSV文件本身存在编码问题，读取时显式指定编码：

examples = pd.read_csv(FLAGS.csv_input, encoding='utf-8')
# 若utf-8报错，尝试encoding='gbk'或'latin-1'

4. 更换TFRecordWriter的兼容写法 #

针对TensorFlow版本兼容问题，改用tf.io.TFRecordWriter替代旧API：

writer = tf.io.TFRecordWriter(FLAGS.output_path)

内容的提问来源于stack exchange，提问作者user22776335