生成 tfrecords 时出现 UnicodeDecodeError

如何解决生成 tfrecords 时出现 UnicodeDecodeError

我正在尝试为 png 图像和 csv 标签生成 tfrecords，以使用用于检测对象的 tensorflow API 来训练对象检测模型。我正在使用教程中的脚本，但出现此错误：UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe9 in position 65: invalid continuation byte 我不知道如何解决它。你们有什么想法吗？？

这是生成 tfrecords 的程序：

"""
Usage:
  # From tensorflow/models/
  # Create train data:
  python preprocessing/csv_to_tfrecords.py --csv_input=data/train_labels.csv  --output_path=data/train.record
  # Create test data:
  python preprocessing/csv_to_tfrecords.py --csv_input=data/test_labels.csv  --output_path=data/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 as tf

from PIL import Image
from object_detection.utils import dataset_util
from collections import namedtuple,OrderedDict

flags = tf.compat.v1.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 == 'capsule':
        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.io.gfile.GFile(os.path.join(path,'{}'.format(group.filename)),'rb') as fid:
        encoded_png = fid.read()
    encoded_png_io = io.BytesIO(encoded_png)
    image = Image.open(encoded_png_io)
    width,height = image.size

    filename = group.filename.encode('utf8')
    image_format = b'png'
    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_png),'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.compat.v1.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.compat.v1.app.run()

在尝试生成 tfrecords 后，我得到了回溯：

python preprocessing/csv_to_tfrecords.py --csv_input=data/train_labels.csv  --output_path=data/train.record
2021-05-31 21:34:20.376813: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2021-05-31 21:34:20.377348: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
Traceback (most recent call last):
  File "preprocessing/csv_to_tfrecords.py",line 100,in <module>
    tf.compat.v1.app.run()
  File "C:\Users\user\AppData\Local\Programs\Python\python37\lib\site-packages\tensorflow\python\platform\app.py",line 40,in run
    _run(main=main,argv=argv,flags_parser=_parse_flags_tolerate_undef)
  File "C:\Users\user\AppData\Local\Programs\Python\python37\lib\site-packages\absl\app.py",line 303,in run
    _run_main(main,args)
  File "C:\Users\user\AppData\Local\Programs\Python\python37\lib\site-packages\absl\app.py",line 251,in _run_main
    sys.exit(main(argv))
  File "preprocessing/csv_to_tfrecords.py",line 91,in main
    tf_example = create_tf_example(group,path)
  File "preprocessing/csv_to_tfrecords.py",line 46,in create_tf_example
    encoded_png = fid.read()
  File "C:\Users\user\AppData\Local\Programs\Python\python37\lib\site-packages\tensorflow\python\lib\io\file_io.py",line 117,in read     
    self._preread_check()
  File "C:\Users\user\AppData\Local\Programs\Python\python37\lib\site-packages\tensorflow\python\lib\io\file_io.py",line 80,in _preread_check
    compat.path_to_str(self.__name),1024 * 512)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe9 in position 65: invalid continuation byte

解决方法

pd.read_csv(FLAGS.csv_input) 行存在一些问题。尝试在 csv 文件中使用不同的 encoding 方案。你可以参考这个answer。