Lambda层:函数构建代码之外的一个op正在传递一个“图”张量

Question

我有一个类似于这篇文章的问题：Tensorflow 2.1.0 - An op outside of the function building code is being passed a "Graph" tensor

我的模型包括一个CNN的TimeDistributed包装器，它的输入层首先被lambda函数规范化：

    # ENCODER
    # video input
    frames = 10
    video_input = tf.keras.Input(shape=(frames, 256, 256, 3))

    # cnn 1 frame input
    frame_in = Input(shape=(256,256,3), name='frame_input')
    #normalisation layer
    cnn = Lambda(lambda inputs: frame_in / 255)(frame_in)
    # add cnn layers + activations
    cnn = Conv2D(filters=num_filters[0], kernel_size=(4,4), strides=(4,4), padding='same', activation = 'relu', data_format='channels_last', name = 'Layer_1')(cnn) #input_shape=(64,64,3), data_format='channels_last'), name = 'Layer_1')(frame_in)
    cnn = Conv2D(filters=num_filters[1], kernel_size=(4,4), strides=(4,4), padding='same', activation = 'relu', name = 'Layer_2')(cnn)
    cnn = Conv2D(filters=num_filters[2], kernel_size=(4,4), strides=(2,2), padding='same', activation = 'relu', name = 'Layer_3')(cnn)
    cnn = Conv2D(filters=num_filters[3], kernel_size=(4,4), strides=(2,2), padding='same', activation = 'relu', name = 'Layer_4')(cnn)
    cnn = Conv2D(filters=num_filters[4], kernel_size=(4,4), strides=(1,1), padding='valid', activation = 'relu', name = 'Layer_5')(cnn)
    # flatten
    cnn = Flatten()(cnn)
    #time distributed
    time_dist_cnn = Model(inputs=frame_in, outputs=cnn, name='Time_Distributed_CNN')
    time_dist_0 = TimeDistributed(time_dist_cnn)(video_input)

错误是相同的：

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: frame_input:0

我知道问题几乎是一样的，并且源于lambda表达式的使用，但我不知道如何在这种情况下解决它。

Answer 1

如果在急切模式下运行，则tensorflow操作将检查输入是否为tensorflow.python.framework.ops.EagerTensor类型，而keras是否作为DAG实现。因此，如果对急切模式的输入是tensorflow.python.framework.ops.Tensor的，那么这将引发错误。

您可以将输入类型更改为EagerTensor，方法是通过使用tf.config.experimental_run_functions_eagerly(True)告诉tensorflow以急切模式运行keras。添加这个声明可以解决你的问题。

或者，通过在程序顶部添加tf.compat.v1.disable_eager_execution()来禁用急切的执行，也将成功地运行程序。

例如，这个程序抛出您所面临的错误-

用于复制错误的代码-

import numpy as np
import tensorflow as tf
print(tf.__version__)
from tensorflow.keras import layers, losses, models

def get_loss_fcn(w):
    def loss_fcn(y_true, y_pred):
        loss = w * losses.mse(y_true, y_pred)
        return loss
    return loss_fcn

data_x = np.random.rand(5, 4, 1)
data_w = np.random.rand(5, 4)
data_y = np.random.rand(5, 4, 1)

x = layers.Input([4, 1])
w = layers.Input([4])
y = layers.Activation('tanh')(x)
model = models.Model(inputs=[x, w], outputs=y)
loss = get_loss_fcn(model.input[1])

model.compile(loss=loss)
model.fit((data_x, data_w), data_y)

输出-

2.2.0
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     59     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 60                                         inputs, attrs, num_outputs)
     61   except core._NotOkStatusException as e:

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: input_8:0

During handling of the above exception, another exception occurred:

_SymbolicException                        Traceback (most recent call last)
8 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     72       raise core._SymbolicException(
     73           "Inputs to eager execution function cannot be Keras symbolic "
---> 74           "tensors, but found {}".format(keras_symbolic_tensors))
     75     raise e
     76   # pylint: enable=protected-access

_SymbolicException: Inputs to eager execution function cannot be Keras symbolic tensors, but found [<tf.Tensor 'input_8:0' shape=(None, 4) dtype=float32>]

解决方案1 -将这个tf.config.experimental_run_functions_eagerly(True)添加到程序的顶部，成功地运行程序。同时，在程序顶部添加tf.compat.v1.disable_eager_execution()以禁用急切的执行，也可以成功地运行程序。

固定码-

import numpy as np
import tensorflow as tf
print(tf.__version__)
from tensorflow.keras import layers, losses, models

tf.config.experimental_run_functions_eagerly(True)

def get_loss_fcn(w):
    def loss_fcn(y_true, y_pred):
        loss = w * losses.mse(y_true, y_pred)
        return loss
    return loss_fcn

data_x = np.random.rand(5, 4, 1)
data_w = np.random.rand(5, 4)
data_y = np.random.rand(5, 4, 1)

x = layers.Input([4, 1])
w = layers.Input([4])
y = layers.Activation('tanh')(x)
model = models.Model(inputs=[x, w], outputs=y)
loss = get_loss_fcn(model.input[1])

model.compile(loss=loss)
model.fit((data_x, data_w), data_y)

print('Done.')

输出-

2.2.0
1/1 [==============================] - 0s 1ms/step - loss: 0.0000e+00
Done.

解决方案2 -也请尝试下面的解决方案，您可以尝试按下面的方式修改并查看是否有效-

1)创建normalize_input函数如下：

def normalize_input(inputs):
    norm_input = inputs / 255
    return norm_input

2)修改Lambda层如下：

cnn = tf.keras.layers.Lambda(function=normalize_input)([frame_in])

希望这能回答你的问题。学习愉快。