tfrecords_write.py
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
#定义一个writer->转化数据的格式->包装好一个example->将example序列化->写入
#将数据转化成相应的格式
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]))
mnist = input_data.read_data_sets('../MNIST_data',one_hot=True,dtype=tf.uint8)
images = mnist.train.images
labels = mnist.train.labels
pixels = images.shape[1]
num_examples = mnist.train.num_examples
filename = 'output.tfrecords'
writer = tf.python_io.TFRecordWriter(filename)
for i in range(num_examples):
image_raw = images[i].tostring()
example = tf.train.Example(features=tf.train.Features(feature={
'pixels':_int64_feature(pixels),
'label':_int64_feature(np.argmax(labels[i])),
'image_raw':_bytes_feature(image_raw)
}))
writer.write(example.SerializeToString())
writer.close()
tfrecords_read.py
import tensorflow as tf
#定义reader->read一个example->解析->打印
reader = tf.TFRecordReader()
#使用队列来维护输入文件列表
filename_queue = tf.train.string_input_producer(['output.tfrecords'])
#获取序列化的数据,每次只读取一个
_,serialize_examples = reader.read(filename_queue)
#解析数据
features = tf.parse_single_example(
serialize_examples,
features={
'image_raw':tf.FixedLenFeature([],tf.string),
'pixels':tf.FixedLenFeature([],tf.int64),
'label':tf.FixedLenFeature([],tf.int64)
}
)
#将字符串解析成像素数组
image = tf.decode_raw(features['image_raw'],tf.uint8)
label = tf.cast(features['label'],tf.int32)
pixels = tf.cast(features['pixels'],tf.int32)
with tf.Session() as sess:
#启动多线程
threads = tf.train.start_queue_runners(sess,tf.train.Coordinator())
for i in range(10):
#每次都随机读取一个样例
print(sess.run([label]))