Question

为了将3种不同的激活函数应用于最后一个Dense层的3列，我正在使用Lambda层。首先，我拆分然后重新组装输出。到目前为止，尚未应用任何实际的激活，因为我发现以下内容在模型拟合步骤给了我一个错误：

def createModel():
in_put = Input(shape=(3300,))
layer1 = Dense(512, activation='relu')(in_put)
layer2 = Dense(1024, activation='relu')(layer1)
layer3 = Dense(32, activation='relu')(layer2)
out_put = Dense(3)(layer3)

#splitting output into 3 columns for further activation
theta = Lambda(lambda x: x[:,0], output_shape=(1,))(out_put)
phi = Lambda(lambda x: x[:,1], output_shape=(1,))(out_put)
r = Lambda(lambda x: x[:,2], output_shape=(1,))(out_put)

#combining the activated layers (activation has not been implemented yet) 
out_put_a = Lambda(lambda x: K.stack([x[0], x[1], x[2]]),output_shape=(3,),  name="output")([theta, phi, r])

model = Model(inputs=in_put, outputs=out_put_a)
return model

my_network=createModel()

batch_size = 1000
epochs = 1

my_network.compile(optimizer='rmsprop', loss='mean_squared_error')
history = my_network.fit_generator(generator=training_generator, epochs=epochs, 
                validation_data=testing_generator)

它崩溃并显示以下错误：

InvalidArgumentError：找到2个根错误。（0）无效的参数：形状不兼容：[3]与[1000] [[{{节点培训/ RMSprop / gradients / loss / output_loss / mul_grad / BroadcastGradientArgs}}]] [[loss / mul / _55]] （1）无效的参数：不兼容的形状：[3]与[1000] [[{{节点培训/ RMSprop / gradients / loss / output_loss / mul_grad / BroadcastGradientArgs}}]] 0次成功操作。忽略0个派生错误。>

同时，下面的代码（没有Lambda层也可以正常工作）：

def createModel():
in_put = Input(shape=(3300,))
layer1 = Dense(512, activation='relu')(in_put)
layer2 = Dense(1024, activation='relu')(layer1)
layer3 = Dense(32, activation='relu')(layer2)
out_put = Dense(3)(layer3)

model = Model(inputs=in_put, outputs=out_put)
return model

my_network=createModel()

batch_size = 1000
epochs = 1

my_network.compile(optimizer='rmsprop', loss='mean_squared_error')
history = my_network.fit_generator(generator=training_generator, epochs=epochs, 
                validation_data=testing_generator)

谁能指出lambda层出了什么问题？

具有Lambda图层的Keras，用于自定义激活

0 个答案: