Keras模型支持多种输出。因此,如果不应该训练鉴别器,只需将discriminator包含到keras模型中,freeze包含discriminator层。在
下一个问题是如何结合自动编码器损耗和鉴别器损耗。幸运的是kerasmodel.compile支持减肥。如果自动编码器是您的第一个输出,而鉴别器是您的第二个输出,那么您可以做类似loss_weights=[1, -1]的操作。因此,一个更好的鉴别器对自动编码器来说就更糟了。在
编辑:下面是一个示例,如何实现对手网络:# Build your architecture
auto_encoder_input = Input((5,))
auto_encoder_net = Dense(10)(auto_encoder_input)
auto_encoder_output = Dense(5)(auto_encoder_net)
discriminator_net = Dense(20)(auto_encoder_output)
discriminator_output = Dense(5)(discriminator_net)
# Define outputs of your model
train_autoencoder_model = Model(auto_encoder_input, [auto_encoder_output, discriminator_output])
train_discriminator_model = Model(auto_encoder_input, discriminator_output)
# Compile the models (compile the first model and then change the trainable attribute for the second)
for layer_index, layer in enumerate(train_autoencoder_model.layers):
layer.trainable = layer_index < 3
train_autoencoder_model.compile('Adam', loss=['mse', 'mse'], loss_weights=[1, -1])
for layer_index, layer in enumerate(train_discriminator_model.layers):
layer.trainable = layer_index >= 3
train_discriminator_model.compile('Adam', loss='mse')
# A simple example how a training can look like
for i in range(10):
auto_input = np.random.sample((10,5))
discrimi_output = np.random.sample((10,5))
train_discriminator_model.fit(auto_input, discrimi_output, steps_per_epoch=5, epochs=1)
train_autoencoder_model.fit(auto_input, [auto_input, discrimi_output], steps_per_epoch=1, epochs=1)
正如您所见,使用keras构建一个对手模型并没有多少魔力。在