无法将 ndarray 转换为 Tensor 或 TensorFlow 模型中出现运算错误

我正在 TensorFlow 中实现 Wasserstein DCGAN。运行此行时会发生错误：train_image = sess.run(image_batch)。处理这个异常会抛出另一个异常

Fetch argument array([[[0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        ...,
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0]],

       [[0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        ...,
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0]],

       [[0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        ...,
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0]],

       ...,

       [[0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        ...,
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0]],

       [[0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        ...,
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0]],

       [[0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        ...,
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0],
        [0, 0, 0, ..., 0, 0, 0]]], dtype=uint8) has invalid type <class 'numpy.ndarray'>, must be a string or Tensor. (Can not convert a ndarray into a Tensor or Operation.)

我正在使用使用此命令获取的 MNIST 数据集 -->

from keras.datasets import mnist (X_train, Y_train), (X_test, Y_test) = mnist.load_data()

完整的源代码：https://github.com/tanmay-bhatnagar/W-DCGAN https://github.com/tanmay-bhatnagar/W-DCGAN使用 TensorFlow 1.4.1 和 python 3.6 以及所有其他库的最新版本。 请询问任何其他需要的详细信息。

通过之前(X_train, Y_train), (X_test, Y_test)，确保您正在使用tf.convert_to_tensor() https://www.tensorflow.org/api_docs/python/tf/convert_to_tensor将它们转换为代码中的张量。