我希望能够将几个层放在一起,但在指定输入之前,如下所示:
# conv is just a layer, no application
conv = Conv2D(64, (3,3), activation='relu', padding='same', name='conv')
# this doesn't work:
bn = BatchNormalization()(conv)
请注意,如果可以避免,我不想指定输入或其形状,我想稍后将其用作多个输入的共享层。
有没有办法做到这一点?以上给出了以下错误:
>>> conv = Conv2D(64, (3,3), activation='relu', padding='same', name='conv')
>>> bn = BatchNormalization()(conv)
Traceback (most recent call last):
File "/home/mitchus/anaconda3/envs/tf/lib/python3.6/site-packages/keras/engine/topology.py", line 419, in assert_input_compatibility
K.is_keras_tensor(x)
File "/home/mitchus/anaconda3/envs/tf/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 393, in is_keras_tensor
raise ValueError('Unexpectedly found an instance of type `' + str(type(x)) + '`. '
ValueError: Unexpectedly found an instance of type `<class 'keras.layers.convolutional.Conv2D'>`. Expected a symbolic tensor instance.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/mitchus/anaconda3/envs/tf/lib/python3.6/site-packages/keras/engine/topology.py", line 552, in __call__
self.assert_input_compatibility(inputs)
File "/home/mitchus/anaconda3/envs/tf/lib/python3.6/site-packages/keras/engine/topology.py", line 425, in assert_input_compatibility
str(inputs) + '. All inputs to the layer '
ValueError: Layer batch_normalization_4 was called with an input that isn't a symbolic tensor. Received type: <class 'keras.layers.convolutional.Conv2D'>. Full input: [<keras.layers.convolutional.Conv2D object at 0x7f3f6e54b748>]. All inputs to the layer should be tensors.
获取 conv 层的输出也不起作用:
>>> bn = BatchNormalization()(conv.output)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/mitchus/anaconda3/envs/tf/lib/python3.6/site-packages/keras/engine/topology.py", line 941, in output
' has no inbound nodes.')
AttributeError: Layer conv has no inbound nodes.
最佳答案
尝试这个:
def create_shared_layers():
layers = [
Conv2D(64, (3,3), activation='relu', padding='same', name='conv'),
BatchNormalization()
]
def shared_layers(x):
for layer in layers:
x = layer(x)
return x
return shared_layers
稍后,您可以执行以下操作:
shared_layers = create_shared_layers()
...
h1 = shared_layers(x1)
h2 = shared_layers(x2)
关于python-3.x - 如何在不指定输入(或输入形状)的情况下在 keras 2 功能 API 中链接/组合层,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/45439492/