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
我的模型包含一个围绕 CNN 的 TimeDistributed 包装器,其输入层首先由 lambda 函数标准化:
# 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
我知道问题几乎相同,并且源于 lambda 表达式的使用,但我不确定如何在这种情况下解决它。
最佳答案
如果在 eager 模式下运行,tensorflow 操作将检查输入的类型是否为 tensorflow.python.framework.ops.EagerTensor
keras ops 被实现为 DAG。因此,如果急切模式的输入为 tensorflow.python.framework.ops.Tensor
,然后这会引发错误。
您可以通过使用tf.config.experimental_run_functions_eagerly(True)
显式告诉tensorflow在keras的eager模式下运行,将输入类型更改为EagerTensor 。添加此语句应该可以解决您的问题。
或者,也可以通过添加 tf.compat.v1.disable_eager_execution()
来禁用急切执行。程序顶部的也会成功运行程序。
例如,该程序会引发您面临的错误 -
重现错误的代码-
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 - 添加此 tf.config.experimental_run_functions_eagerly(True)
在程序的顶部,程序成功运行。还添加tf.compat.v1.disable_eager_execution()
在程序顶部禁用急切执行也可以成功运行程序。
固定代码 -
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,您可以尝试如下修改,看看是否有效 -
1) 创建normalize_input
功能如下:
def normalize_input(inputs):
norm_input = inputs / 255
return norm_input
2) 修改Lambda
图层如下:
cnn = tf.keras.layers.Lambda(function=normalize_input)([frame_in])
希望这能回答您的问题。快乐学习。
关于python - Lambda层: An op outside of the function building code is being passed a “Graph” tensor,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/62314906/