TensorFlow实战框架Chp7--TFRecord样例程序--写入、读取

• TensorFlow实战框架Chp7–TFRecord样例程序–写入、读取
• 保存TFRecord文件的语法，可参考博客：https://blog.csdn.net/xierhacker/article/details/72357651

---

• 写入

# -*- coding: utf-8 -*-
"""
Created on Thu Jul  5 21:17:21 2018

@author: muli
"""

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np


# 定义函数转化变量类型。
def _int64_feature(value):
    return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))

def _bytes_feature(value):
    return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))

# 将数据转化为tf.train.Example格式。
def _make_example(pixels, label, image):
    image_raw = image.tostring()
    example = tf.train.Example(features=tf.train.Features(feature={
        'pixels': _int64_feature(pixels),
        'label': _int64_feature(np.argmax(label)),
        'image_raw': _bytes_feature(image_raw)
    }))
    return example

# 读取mnist训练数据。
mnist = input_data.read_data_sets("./datasets/MNIST_data",dtype=tf.uint8, one_hot=True)
images = mnist.train.images
labels = mnist.train.labels
pixels = images.shape[1]
num_examples = mnist.train.num_examples

# 输出包含训练数据的TFRecord文件。
with tf.python_io.TFRecordWriter("./TFRecord/output.tfrecords") as writer:
    for index in range(num_examples):
        example = _make_example(pixels, labels[index], images[index])
        writer.write(example.SerializeToString())
print("TFRecord训练文件已保存。")

# 读取mnist测试数据。
images_test = mnist.test.images
labels_test = mnist.test.labels
pixels_test = images_test.shape[1]
num_examples_test = mnist.test.num_examples

# 输出包含测试数据的TFRecord文件
with tf.python_io.TFRecordWriter("./TFRecord/output_test.tfrecords") as writer:
    for index in range(num_examples_test):
        example = _make_example(
            pixels_test, labels_test[index], images_test[index])
        writer.write(example.SerializeToString())
print("TFRecord测试文件已保存。")

• 读取

# -*- coding: utf-8 -*-
"""
Created on Fri Jul  6 10:10:17 2018

@author: muli
"""

import tensorflow as tf

# 读取文件
reader = tf.TFRecordReader()
# 创建一个队列来维护输入文件列表，里面包含多个文件
filename_queue = tf.train.string_input_producer(
        ["./TFRecord/output.tfrecords"])

# 读取列表中的文件
_,serialized_example = reader.read(filename_queue)

# 解析读取的样例
features = tf.parse_single_example(
    serialized_example,
    features={
        'image_raw':tf.FixedLenFeature([],tf.string),
        'pixels':tf.FixedLenFeature([],tf.int64),
        'label':tf.FixedLenFeature([],tf.int64)
    })

# 数据格式转换
images = tf.decode_raw(features['image_raw'],tf.uint8)
labels = tf.cast(features['label'],tf.int32)
pixels = tf.cast(features['pixels'],tf.int32)

# 创建会话
sess = tf.Session()

# 声明一个tf.train.Coordinator类来协同多个进程
coord = tf.train.Coordinator()
# 启动多线程处理输入数据
threads = tf.train.start_queue_runners(sess=sess,coord=coord)

for i in range(10):
    image, label, pixel = sess.run([images, labels, pixels])
    print("正在处理第"+str(i+1)+"个文件...")