generate_tfrecord.py原作者版本不同，折腾一下午不报utf-8错误终于能生成recore文件，不过没有数据
且还是报错说键错误。实在解决不了，求
源代码如下：
from __future__ import division
from __future__ import print_function
from __future__ import absolute_import
import os
import io
import pandas as pd
from PIL import Image
from collections import namedtuple
import tensorflow as tf
# CSV文件的位置
csv_input = 'D:/AAAAA/tf5_img/img_train/img_train.csv'
# TFRecords的输出位置及文件名
output_path = 'D:/AAAAA/tf5_img/img_train.record'
# 图像数据的位置
image_dir = 'D:/AAAAA/tf5_img/'
def class_text_to_int(row_label):
if row_label == 'Xiaomi Smart Camera':
return 0
elif row_label == 'Water cup':
return 1
elif row_label == 'Hello':
return 2
elif row_label == 'Glasses box':
return 3
elif row_label == 'battery':
return 4
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_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': tf.train.Feature(int64_list=tf.train.Int64List(value=[height])),
'image/width': tf.train.Feature(int64_list=tf.train.Int64List(value=[width])),
'image/filename': tf.train.Feature(bytes_list=tf.train.BytesList(value=[filename])),
'image/source_id': tf.train.Feature(bytes_list=tf.train.BytesList(value=[filename])),
'image/encoded': tf.train.Feature(bytes_list=tf.train.BytesList(value=[encoded_jpg])),
'image/format': tf.train.Feature(bytes_list=tf.train.BytesList(value=[image_format])),
'image/object/bbox/xmin': tf.train.Feature(float_list=tf.train.FloatList(value=xmins)),
'image/object/bbox/xmax': tf.train.Feature(float_list=tf.train.FloatList(value=xmaxs)),
'image/object/bbox/ymin': tf.train.Feature(float_list=tf.train.FloatList(value=ymins)),
'image/object/bbox/ymax': tf.train.Feature(float_list=tf.train.FloatList(value=ymaxs)),
'image/object/class/text': tf.train.Feature(bytes_list=tf.train.BytesList(value=classes_text)),
'image/object/class/label': tf.train.Feature(int64_list=tf.train.Int64List(value=classes)),
}))
return tf_example
def main():
writer = tf.io.TFRecordWriter(output_path)
path = os.path.join(os.getcwd(), image_dir)
examples = pd.read_csv(csv_input,encoding='gbk')
grouped = split(examples, 'filename')
for group in grouped:
tf_example = create_tf_example(group, path)
writer.write(tf_example.SerializeToString())
writer.close()
if __name__ == '__main__':
main()
```****
报错信息：
