TFRecord文件查看包含的所有Features代码

# 1. 写入过程
# 一张图片，我写入了其内容，label，长和宽几个信息
tf_example = tf.train.Example(
    features=tf.train.Features(feature={
      'encoded': bytes_feature(encoded_jpg),
      'label': int64_feature(label),
      'height': int64_feature(height),
      'width': int64_feature(width)}))
# 2. 读取过程
# 定义解析的TFRecord数据格式
def _parse_image(example_proto):
   features = {'encoded':tf.FixedLenFeature((),tf.string),
  'label': tf.FixedLenFeature((), tf.int64),
  'height': tf.FixedLenFeature((), tf.int64),
  'width': tf.FixedLenFeature((), tf.int64)
}
return tf.parse_single_example(example_proto, features)
 
# TFRecord数据按照Feature解析出对应的真实数据
ds = ds.map(lambda x : _parse_image(x), num_parallel_calls=4)

#!/usr/bin/python
# -*- coding: utf-8 -*-
 
import sys
import tensorflow as tf
 
# 用法：python trackTFRecord.py True file1 file2 
# trackTFRecord.py 就是当前这个py文件
# True 表示是否输出具体的数据
# file1 file2 表示的是需要查看的TFRecord文件的绝对路径
# 输出说明：tf.float32对应TFRecord的FloatList，tf.int64对应Int64List，tf.string对应BytesList
def main():
  print('TFRecord文件个数为{0}个'.format(len(sys.argv)-2))
  for i in range(2, len(sys.argv)):
    filepath = sys.argv[i]
    with tf.Session() as sess:
      filenames = [filepath]
      # 加载TFRecord数据
      ds = tf.data.TFRecordDataset(filenames)
      ds = ds.batch(10)
      ds = ds.prefetch(buffer_size=tf.contrib.data.AUTOTUNE)
      iterator = ds.make_one_shot_iterator()
      # 为了加快速度，仅仅简单拿一组数据看下结构
      batch_data = iterator.get_next()
      res = sess.run(batch_data)
      serialized_example = res[0]
      example_proto = tf.train.Example.FromString(serialized_example)
      features = example_proto.features
      print('{0} 信息如下：'.format(filepath))
      for key in features.feature:
        feature = features.feature[key]
        ftype = None
        fvalue = None
        if len(feature.bytes_list.value) > 0:
          ftype = 'bytes_list'
          fvalue = feature.bytes_list.value
          
        if len(feature.float_list.value) > 0:
          ftype = 'float_list'
          fvalue = feature.float_list.value
          
        if len(feature.int64_list.value) > 0:
          ftype = 'int64_list'
          fvalue = feature.int64_list.value
        
        result = '{0} : {1}'.format(key, ftype)
        if 'True' == sys.argv[1]:
          result = '{0} : {1}'.format(result, fvalue)
        print(result) 
 
if __name__ == "__main__":
  main()

import tensorflow as tf
 
filename = "/Users/zhanhaitao/Desktop/1.png"
# 使用tf.read_file读进图片数据
image = tf.read_file(filename)
# 主要是为了获取图片的宽高
image_jpeg = tf.image.decode_jpeg(image, channels=3, name="decode_jpeg_picture")
# reshape图片到原始大小2500x2000x3
image_jpeg = tf.reshape(image_jpeg, shape=(2500,2000,3))
# 获取图片shape数据
img_shape = image_jpeg.shape
width = img_shape[0]
height = img_shape[1]
# 将原图片tensor生成bytes对象， image将保存到tfrecord
sess = tf.Session()
image = sess.run(image)
sess.close()
# 定义TFRecords文件的保存路径及其文件名
path_none = "/Users/zhanhaitao/Desktop/a.tfrecord"
# 定义不同压缩选项的TFRecordWriter
writer_none = tf.python_io.TFRecordWriter(path_none, options=None)
# 将外层features生成特定格式的example
example_none = tf.train.Example(features=tf.train.Features(feature={
"float_val":tf.train.Feature(float_list=tf.train.FloatList(value=[9.99])),
"width":tf.train.Feature(int64_list=tf.train.Int64List(value=[width])),
"height":tf.train.Feature(int64_list=tf.train.Int64List(value=[height])),
"image_raw":tf.train.Feature(bytes_list=tf.train.BytesList(value=[image]))
}))
# example系列化字符串
example_str_none = example_none.SerializeToString()
# 将系列化字符串写入协议缓冲区
writer_none.write(example_str_none)
 
# 关闭TFRecords文件操作接口
writer_none.close()
 
print("finish to write data to tfrecord file!")

python trackTFRecord.py False /Users/zhanhaitao/Desktop/a.tfrecord
# 结果，其中bytes_list对应tf.string，int64_list对应tf.int64 float_list对应tf.float32
# image_raw : bytes_list
# width : int64_list
# float_val : float_list
# height : int64_list