python - 值错误 : TensorFlow requires that the following symbols must be defined before the loop

Question

我正在尝试使用 tf.data API. 创建一个输入管道我有 3D 数据并使用普通的 NumPy 操作，我最终会得到一个尺寸为 [?,256x256x3x100] 的数组，可以将其视为 100 帧，每个 256x256x3 大小。

import glob
import os
import numpy as np
import tensorflow.compat.v1 as tf

def readfile(filenames):
    flag = 0
    for name in filenames:
        string = tf.read_file(name)
        image = tf.image.decode_image(string, channels=3)
        if flag == 0:
            bunch = image
            flag = 1
        else:
            bunch = tf.concat([bunch,image],1)   
    return bunch

with tf.device("/cpu:0"):
    train_files = []
    for s in [x[0] for x in os.walk("path/to/data/folders")]:
        if(s == "path/to/data/folders"):
            continue
        train_files.append(glob.glob(s+"/*.png"))
    # shape of train_files is [5,100]
    train_dataset = tf.data.Dataset.from_tensor_slices(train_files)
    train_dataset = train_dataset.map(readfile, num_parallel_calls=16)

我认为发生错误是因为 'bunch' 正在改变 for 循环中的大小。错误:

ValueError                                Traceback (most recent call last)
<ipython-input-13-c2f88ca344dc> in <module>
      22     train_dataset = train_dataset.map(
 ---> 23             readfile, num_parallel_calls=16)


ValueError: in converted code:

ValueError: TensorFlow requires that the following symbols must be defined before the loop: ('bunch',)

如何正确读取数据？

编辑

什么对我有用:

def readfile(filenames):
    flag = 0
    name = filenames[0]
    string = tf.read_file(name)
    image = tf.image.decode_image(string, channels=3)
    bunch = image
    for name in filenames:
        string = tf.read_file(name)
        image = tf.image.decode_image(string, channels=3)
        if flag == 0:
            bunch = image
            flag = 1
        else:
            bunch = tf.concat([bunch,image],1)   
    return bunch

所以我不确定为什么需要初始化 bunch在循环之前，当第一次迭代时应该注意 bunch = image .可能是因为 flag 没有定义为张量所以 bunch = image从来没有真正运行过？

Answer 1

变量 bunch在函数内创建 readfile()因此出现错误，因为在运行时无法在循环内创建变量。解决方法是移动变量 bunch 的声明。在循环之外。代码示例如下:

import glob
import os
import numpy as np
import tensorflow.compat.v1 as tf

def readfile(filenames):
    flag = 0
    bunch = <some_appropriate_initialization>
    for name in filenames:
        string = tf.read_file(name)
        image = tf.image.decode_image(string, channels=3)
        if flag == 0:
            bunch = image
            flag = 1
        else:
            bunch = tf.concat([bunch,image],1)   
    return bunch

# Rest of the code