Question

我正在尝试读取Keras中的中间层的输出：

input_dim = 30
encoding_dim = 14

input_layer = Input(shape=(input_dim, ))

encoder = Dense(encoding_dim, activation="tanh", 
                activity_regularizer=regularizers.l1(10e-5))(input_layer)
encoder = Dense(int(encoding_dim / 2), activation="relu")(encoder)

decoder = Dense(int(encoding_dim / 2), activation='tanh',name='decoder_input')(encoder)
decoder = Dense(input_dim, activation='relu',name='decoder_output')(decoder)

autoencoder = Model(inputs=input_layer, outputs=decoder)


#evaluate decoder...
layer_output_dec =  Model(inputs=autoencoder.layers[3].input,
                             outputs=autoencoder.layers[4].output)

但是我得到了错误：

/usr/local/lib/python2.7/site-packages/keras/engine/network.pyc in __init__(self, *args, **kwargs)
     89                 'inputs' in kwargs and 'outputs' in kwargs):
     90             # Graph network
---> 91             self._init_graph_network(*args, **kwargs)
     92         else:
     93             # Subclassed network

/usr/local/lib/python2.7/site-packages/keras/engine/network.pyc in _init_graph_network(self, inputs, outputs, name)
    181                           'instantiated via '
    182                           '`tensor = tf.layers.Input(shape)`.\n'
--> 183                           'The tensor that caused the issue was: ' +
    184                           str(x.name))
    185         for x in self.outputs:

AttributeError: 'Model' object has no attribute 'name'

我认为该错误是由于缺少图层名称造成的，但没有帮助。任何帮助表示赞赏。

Answer 1

这将采用已经连接到之前输入的输入。无法使该模型正常运行。

#evaluate decoder...
layer_output_dec =  Model(inputs=autoencoder.layers[3].input,
                         outputs=autoencoder.layers[4].output)

您需要合适的编码器和解码器型号：

#encoder
input_tensor = Input(shape=(input_dim, ))

encoderOut = Dense(encoding_dim, activation="tanh", 
                activity_regularizer=regularizers.l1(10e-5))(input_tensor)
encoderOut = Dense(int(encoding_dim / 2), activation="relu")(encoderOut)

encoder = Model(input_tensor, encoderOut)


#decoder
decoder_input = Input(shape=(int(encoding_dim / 2),))
decoderOut = Dense(int(encoding_dim / 2), activation='tanh',name='decoder_input')(decoder_input)
decoderOut = Dense(input_dim, activation='relu',name='decoder_output')(decoderOut)

decoder = Model(decoder_input, decoderOut)

#autoencoder
autoInput = Input(shape=(input_dim, ))
encoderOut = encoder(autoInput)
decoderOut = decoder(encoderOut)
autoencoder = Model(inputs=autoInput, outputs=decoderOut)

根据需要使用三种模型。

对于您的问题，请使用decoder作为模型。

Keras的“模型”对象没有属性“名称”

1 个答案: