数据读取之TFRecords

来源：互联网发布：继承多态 java 编辑：程序博客网时间：2024/06/09 22:42

转载自http://blog.csdn.net/u012759136/article/details/52232266 对部分代码做了一些修改

import osimport tensorflow as tffrom PIL import Imagecwd = os.getcwd()

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]))

def create_record():    '''    此处我加载的数据目录如下：    0 -- img1.jpg         img2.jpg         img3.jpg         ...    1 -- img1.jpg         img2.jpg         ...    2 -- ...    ...    '''    writer = tf.python_io.TFRecordWriter("train.tfrecords")    for index, name in enumerate(classes):        class_path = cwd + name + "/"        for img_name in os.listdir(class_path):            img_path = class_path + img_name                img = Image.open(img_path)                img = img.resize((224, 224))            img_raw = img.tobytes() #将图片转化为原生bytes            example = tf.train.Example(features=tf.train.Features(feature={                "label": _int64_feature(index),                'img_raw': _bytes_feature(img_raw)            }))            writer.write(example.SerializeToString())    writer.close()def read_and_decode(filename):    filename_queue = tf.train.string_input_producer([filename])    reader = tf.TFRecordReader()    _, serialized_example = reader.read(filename_queue)    features = tf.parse_single_example(serialized_example,                                       features={                                           'label': tf.FixedLenFeature([], tf.int64),                                           'img_raw' : tf.FixedLenFeature([], tf.string),                                       })    img = tf.decode_raw(features['img_raw'], tf.uint8)    img = tf.reshape(img, [224, 224, 3])    img = tf.cast(img, tf.float32) * (1. / 255) - 0.5    label = tf.cast(features['label'], tf.int32)    return img, labelif __name__ == '__main__':    img, label = read_and_decode("train.tfrecords")    img_batch, label_batch = tf.train.shuffle_batch([img, label],                                                    batch_size=30, capacity=2000,                                                    min_after_dequeue=1000,enqueue_many=True)    #初始化所有的op    init = tf.global_variables_initializer()    with tf.Session() as sess:        sess.run(init)#启动队列

coord = tf.train.Coordinator()        threads = tf.train.start_queue_runners(sess=sess,coord=coord)        for i in range(3):            val, l= sess.run([img_batch, label_batch])            print(val.shape, l)

coord.request_stop()coord.join(threads)sess.close()

在源代码上做了一些修改

1.将Feature函数单独抽象出来

2.tf.train.shuffle_batch中的参数enqueue_many修改成了True,默认是False，区别在于输入[x,y,z]如果enqueue_many默认为False，则输出为[batch_size,x,y,z]，如果设置为True，那么输出就是[batch_size,y,z]

3.将变量初始化修改成了新版的初始化方法(貌似这里用不到)

4.加入了tf.train.Coordinator()

0 0