tensorflow：使用dataset方式读取数据

刚刚使用tensorflow自带的dataset类做数据读取，非常的方便，功能也很强大。终于不需要用队列了。

def _parse_function(filename, label):
  image_string = tf.read_file(filename)
  image_decoded = tf.image.decode_image(image_string)
  #image_resized = tf.image.resize_images(image_decoded, [28, 28])
  return image_decoded, label

chars, char_dict, char_dict_re, train_f_name_list, test_f_name_list, len_test_f, len_train_f = data_init()

def dataset_test():
    # 获取图片名
    tra = tf.constant([imagepath+ '/'+test_f_name_list[i].split()[0] for i in range(100)])
    # 获取label
    labels = tf.constant([test_f_name_list[i].split()[1:] for i in range(100)])
    # 将data和label给 dataset 对象
    tra_data = tf.data.Dataset.from_tensor_slices((tra, labels))
    # 读取data字符串指定的磁盘上的数据，通过_parse_function
    tra_data = tra_data.map(_parse_function)
    # 设置batch size
    tra_data = tra_data.batch(3)
    # 申请iterator
    iterator = tra_data.make_initializable_iterator()
    # 得到数据
    next_element = iterator.get_next()
    with tf.Session() as sess:
        sess.run(iterator.initializer)
        t0 = time.time()
        for i in range(20):
            data = sess.run(next_element)
            tt = time.time()
            print('time:%f shape:%s' % (tt-t0, data[0].shape))
            t0 = tt
dataset_test()

'''
读取速度挺快的
time:0.002507 shape:(3, 32, 280, 3)
time:0.002005 shape:(3, 32, 280, 3)
time:0.002005 shape:(3, 32, 280, 3)
'''

参考文章：URL: https://blog.csdn.net/west_609/article/details/78608541