Question

我遇到以下异常

TypeError: An op outside of the function building code is being passed
a "Graph" tensor. It is possible to have Graph tensors
leak out of the function building context by including a
tf.init_scope in your function building code.
For example, the following function will fail:
  @tf.function
  def has_init_scope():
    my_constant = tf.constant(1.)
    with tf.init_scope():
      added = my_constant * 2
The graph tensor has name: conv2d_flipout/divergence_kernel:0

这还会引发以下异常

tensorflow.python.eager.core._SymbolicException: Inputs to eager execution function cannot be Keras symbolic tensors, but found [<tf.Tensor 'conv2d_flipout/divergence_kernel:0' shape=() dtype=float32>]

运行以下代码时

from __future__ import print_function

import tensorflow as tf
import tensorflow_probability as tfp


def get_bayesian_model(input_shape=None, num_classes=10):
    model = tf.keras.Sequential()
    model.add(tf.keras.layers.Input(shape=input_shape))
    model.add(tfp.layers.Convolution2DFlipout(6, kernel_size=5, padding="SAME", activation=tf.nn.relu))
    model.add(tf.keras.layers.Flatten())
    model.add(tfp.layers.DenseFlipout(84, activation=tf.nn.relu))
    model.add(tfp.layers.DenseFlipout(num_classes))
    return model

def get_mnist_data(normalize=True):
    img_rows, img_cols = 28, 28
    (x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()

    if tf.keras.backend.image_data_format() == 'channels_first':
        x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
        x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
        input_shape = (1, img_rows, img_cols)
    else:
        x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
        x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
        input_shape = (img_rows, img_cols, 1)

    x_train = x_train.astype('float32')
    x_test = x_test.astype('float32')

    if normalize:
        x_train /= 255
        x_test /= 255

    return x_train, y_train, x_test, y_test, input_shape


def train():
    # Hyper-parameters.
    batch_size = 128
    num_classes = 10
    epochs = 1

    # Get the training data.
    x_train, y_train, x_test, y_test, input_shape = get_mnist_data()

    # Get the model.
    model = get_bayesian_model(input_shape=input_shape, num_classes=num_classes)

    # Prepare the model for training.
    model.compile(optimizer=tf.keras.optimizers.Adam(), loss="sparse_categorical_crossentropy",
                  metrics=['accuracy'])

    # Train the model.
    model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1)
    model.evaluate(x_test, y_test, verbose=0)


if __name__ == "__main__":
    train()

问题显然与tfp.layers.Convolution2DFlipout层有关。为什么我会收到这些例外？这是由于我的代码中的逻辑错误导致的还是TensorFlow或TensorFlow概率中的错误？这些错误是什么意思？我该怎么解决？

我正在使用TensorFlow 2.0.0（默认情况下会急切执行）。和TensorFlow概率0.8.0和Python 3.7.4。我还打开了相关问题here和here。

请不要建议我使用TensorFlow 1来延迟执行我的代码（即，在导入TensorFlow之后使用tf.compat.v1.disable_eager_execution()，因为我知道这会使上面的代码运行而不引起提及的异常）或显式创建会话或占位符。

Answer 1

就像我在comment to the Github issue I had opened中所写的那样，可以通过将experimental_run_tf_function方法的参数compile设置为False来部分解决此问题。

但是，如果将experimental_run_tf_function设置为False，并且尝试使用predict方法，则会收到另一个错误。参见this Github issue。

编辑（2020年9月28日）

experimental_run_tf_function在最新版的TF中已删除。但是，在最新版本的TFP（我使用的特定版本在下面列出）中，贝叶斯卷积层（至少是使用Flipout估计器的那个）的问题已修复。参见https://github.com/tensorflow/probability/issues/620#issuecomment-620821990和https://github.com/tensorflow/probability/commit/1574c1d24c5dfa52bdf2387a260cd63a327b1839。

具体来说，我使用了以下版本

tensorflow==2.3.0
tensorflow-probability==0.11.0

我同时使用了密集和卷积的贝叶斯层，在调用experimental_run_tf_function=False时我没有不使用compile。

TypeError：函数构建代码外部的op正在传递图张量

1 个答案: