Question

我为CNN制作了具有多渠道的模型。但是输入只是我的代码中显示的内容。我收到一个错误：AttributeError：'NoneType'对象没有属性'_inbound_nodes' 我看到了其他人的回答，但是我没有使用任何重复向量。

  def ensemble(x_train):

      model_input = input_part(x_train)


      x = Conv1D(6, 5, activation='relu')(model_input)
      conv_pool_model = conv_pool(x) #this is a CNN model

      x_train_1 = x[ : , :227, : ]
      x_train_2 = x[ :, 227:454, : ]
      x_train_3 = x[ :, 454:680, : ]
      x_train_4 = x[ :, 680: , : ]
      # there are four part CNN.
      cnn_p1_model = cnn_p1(x_train_1)
      cnn_p2_model = cnn_p1(x_train_2)
      cnn_p3_model = cnn_p1(x_train_3)
      cnn_p4_model = cnn_p1(x_train_4)

      conca = Concatenate(axis=1)([conv_pool_model, cnn_p1_model, cnn_p2_model, cnn_p3_model, cnn_p4_model])
      x_out = Dropout(0.5)(conca)
      x_out = Dense(2, activation='softmax')(x_out)
      model = Model(inputs = model_input, outputs=x_out, name='conv_pool_cnn')
      return model

这是错误提示：

 Traceback (most recent call last):
    File "D:/Users/11825/source/repos/mutil cnn/hope.py", line 192, in <module>
    cnn_pool_model = ensemble(x_train)
    File "D:/Users/11825/source/repos/mutil cnn/hope.py", line 58, in ensemble
    model = Model(inputs = model_input, outputs=x_out, name='conv_pool_cnn')
    File "D:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
    File "D:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\keras\engine\network.py", line 93, in __init__
    self._init_graph_network(*args, **kwargs)
    File "D:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\keras\engine\network.py", line 231, in _init_graph_network
    self.inputs, self.outputs)
    File "D:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\keras\engine\network.py", line 1366, in _map_graph_network
    tensor_index=tensor_index)
    File "D:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\keras\engine\network.py", line 1353, in build_map
    node_index, tensor_index)
    File "D:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\keras\engine\network.py", line 1353, in build_map
    node_index, tensor_index)
    File "D:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\keras\engine\network.py", line 1353, in build_map
    node_index, tensor_index)
  [Previous line repeated 10 more times]
    File "D:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\site-packages\keras\engine\network.py", line 1325, in build_map
    node = layer._inbound_nodes[node_index]
  AttributeError: 'NoneType' object has no attribute '_inbound_nodes'

Answer 1

Keras层的输入必须是其他Keras层的直接输出。因此，您还需要在图层中进行切片。您可以为此目的使用Lambda层：

  x_train_1 = Lambda(lambda x: x[ : , :227, : ])(x)
  x_train_2 = Lambda(lambda x: x[ :, 227:454, : ])(x)
  x_train_3 = Lambda(lambda x: x[ :, 454:680, : ])(x)
  x_train_4 = Lambda(lambda x: x[ :, 680: , : ])(x)

具有串联AttributeError的Keras：“ NoneType”对象没有属性“ _inbound_nodes”

1 个答案: