python - 运行时错误 : Attempting to capture an EagerTensor without building a function

Question

我用 tf.data.datset API 并使用残差网络。当我为 TensorBoard 运行代码以可视化我的嵌入时，我遇到了这个错误，但是当我使用两层网络时，我没有这个问题。

def load_and_preprocess_from_path_label(path, label):
    return load_and_preprocess_image(path), label

ds = tf.data.Dataset.from_tensor_slices((all_image_paths, all_image_labels))
with tf.Session() as sess:
    # TODO (@omoindrot): remove the hard-coded 10000
    # Obtain the test labels
    image_label_ds = ds.map(load_and_preprocess_from_path_label)
    ds = image_label_ds.shuffle(image_count)

RuntimeError                              Traceback (most recent call last)
<ipython-input-41-ead5d6a54baa> in <module>()
     92         # TODO (@omoindrot): remove the hard-coded 10000
     93         # Obtain the test labels
---> 94         image_label_ds = ds.map(load_and_preprocess_from_path_label)
     95         ds = image_label_ds.shuffle(image_count)
     96 
RuntimeError: Attempting to capture an EagerTensor without building a function.

Answer 1

错误可能是由于 Tensorflow 版本
运行以下代码对我有用:

import tensorflow.compat.v1 as tf

正确的功能:

tf.disable_v2_behavior()