我试图通过添加一个额外的层来将Keras的VAE示例调整为深度网络。
原始代码： 原始VAE代码
更改：
batch_size = 200original_dim = 784latent_dim = 2intermediate_dim_deep = 384 # <<<<<<<intermediate_dim = 256nb_epoch = 20#x = Input(batch_shape=(batch_size, original_dim))x = Dense(intermediate_dim_deep, activation='relu')(x) # 新增层 <<<<<<h = Dense(intermediate_dim, activation='relu')(x)z_mean = Dense(latent_dim)(h)z_log_var = Dense(latent_dim)(h)#def sampling(args): z_mean, z_log_var = args epsilon = K.random_normal(shape=(batch_size, latent_dim), mean=0.) return z_mean + K.exp(z_log_var / 2) * epsilon# note that "output_shape" isn't necessary with the TensorFlow backendz = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_log_var])## we instantiate these layers separately so as to reuse them laterdecoder_h = Dense(intermediate_dim, activation='relu')decoder_d = Dense(intermediate_dim_deep, activation='rely') # 新增层 <<<<<<decoder_mean = Dense(original_dim, activation='sigmoid')h_decoded = decoder_h(z)d_decoded = decoder_d(h_decoded) # 这里增加了一步 <<<<<<<x_decoded_mean = decoder_mean(d_decoded)#def vae_loss(x, x_decoded_mean): xent_loss = original_dim * objectives.binary_crossentropy(x, x_decoded_mean) kl_loss = - 0.5 * K.sum(1 + z_log_var - K.square(z_mean) - K.exp(z_log_var), axis=-1) return xent_loss + kl_loss#vae = Model(x, x_decoded_mean)vae.compile(optimizer='rmsprop', loss=vae_loss)#####编译时我遇到了这个错误：
/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py:1615: UserWarning: Model inputs must come from a Keras Input layer, they cannot be the output of a previous non-Input layer. Here, a tensor specified as input to "model_1" was not an Input tensor, it was generated by layer dense_1.Note that input tensors are instantiated via `tensor = Input(shape)`.The tensor that caused the issue was: None str(x.name))---------------------------------------------------------------------------Exception Traceback (most recent call last)<ipython-input-8-c9010948cdee> in <module>()----> 1 vae = Model(x, x_decoded_mean) 2 vae.compile(optimizer='rmsprop', loss=vae_loss)/usr/local/lib/python2.7/dist-packages/keras/engine/topology.pyc in __init__(self, input, output, name) 1788 'The following previous layers ' 1789 'were accessed without issue: ' +-> 1790 str(layers_with_complete_input)) 1791 for x in node.output_tensors: 1792 computable_tensors.append(x)Exception: Graph disconnected: cannot obtain value for tensor input_1 at layer "input_1". The following previous layers were accessed without issue: []我在仓库中看到了其他示例，似乎这是一种有效的方法。我遗漏了什么吗？
回答：
在添加新的隐藏层时，你覆盖了x变量，因此没有输入层。此外，’rely’是一个有效的激活选项吗？
