Question

我训练模型A并尝试使用名称=“layer_x”的中间层输出作为模型B中的其他输入。

我尝试使用keras doc上的中间层输出 https://keras.io/getting-started/faq/#how-can-i-obtain-the-output-of-an-intermediate-layer

模特A：

inputs = Input(shape=(100,))
dnn = Dense(1024, activation='relu')(inputs)
dnn = Dense(128, activation='relu', name="layer_x")(dnn)
dnn = Dense(1024, activation='relu')(dnn)
output = Dense(10, activation='softmax')(dnn)

模特B：

input_1 = Input(shape=(200,))
input_2 = Input(shape=(100,)) # input for model A

# loading model A
model_a = keras.models.load_model(path_to_saved_model_a)

intermediate_layer_model = Model(inputs=model_a.input, 
                                 outputs=model_a.get_layer("layer_x").output)

intermediate_output = intermediate_layer_model.predict(data)

merge_layer = concatenate([input_1, intermediate_output])
dnn_layer = Dense(512, activation="relu")(merge_layer)
output = Dense(5, activation="sigmoid")(dnn_layer)
model = keras.models.Model(inputs=[input_1, input_2], outputs=output)

当我调试时，我在这一行收到错误：

intermediate_layer_model = Model(inputs=model_a.input, 
                                 outputs=model_a.get_layer("layer_x").output)

File "..", line 89, in set_model
  outputs=self.neural_net_asc.model.get_layer("layer_x").output)
File "C:\WinPython\python-3.5.3.amd64\lib\site-packages\keras\legacy\interfaces.py", line 87, in wrapper
  return func(*args, **kwargs)
File "C:\WinPython\python-3.5.3.amd64\lib\site-packages\keras\engine\topology.py", line 1592, in __init__
  mask = node.output_masks[tensor_index]
AttributeError: 'Node' object has no attribute 'output_masks'

我可以使用get_layer（“layer_x”）输出Tensor。输出和output_mask是None。我是否必须手动设置输出掩码，如何在需要时设置此输出掩码？

Answer 1

有两件事你似乎做错了：

intermediate_output = intermediate_layer_model.predict(data)

当你执行.predict()时，实际上是通过图表传递数据并询问结果是什么。当你这样做时，intermediate_output将是一个numpy数组，而不是你想要的层。

其次，您不需要重新创建新的中间模型。您可以直接使用您感兴趣的model_a部分。

这是一个为我“编译”的代码：

from keras.layers import Input, Dense, concatenate
from keras.models import Model

inputs = Input(shape=(100,))
dnn = Dense(1024, activation='relu')(inputs)
dnn = Dense(128, activation='relu', name="layer_x")(dnn)
dnn = Dense(1024, activation='relu')(dnn)
output = Dense(10, activation='softmax')(dnn)

model_a = Model(inputs=inputs, outputs=output)

# You don't need to recreate an input for the model_a, 
# it already has one and you can reuse it
input_b = Input(shape=(200,))

# Here you get the layer that interests you from model_a, 
# it is still linked to its input layer, you just need to remember it for later
intermediate_from_a = model_a.get_layer("layer_x").output

# Since intermediate_from_a is a layer, you can concatenate it with the other input
merge_layer = concatenate([input_b, intermediate_from_a])
dnn_layer = Dense(512, activation="relu")(merge_layer)
output_b = Dense(5, activation="sigmoid")(dnn_layer)
# Here you remember that one input is input_b and the other one is from model_a
model_b = Model(inputs=[input_b, model_a.input], outputs=output_b)

我希望这是你想要做的。

如果不清楚，请告诉我： - ）

keras使用中间层的输出

1 个答案: