使用VAE的Seq到Seq模型

Question

我尝试将序列与序列模型结合使用VAE，我的代码是：

    encoder_inputs = Input(shape=(None,))
    encoder_emb = Embedding(input_dim=vocab_in_size, 
    output_dim=embedding_dim)
    encoder_lstm =LSTM(units=units, return_sequences=False, return_state=True)
    encoder_outputs, state_h, state_c = 
    encoder_lstm(encoder_emb(encoder_inputs))
    encoder_states = [state_h, state_c]


    latent_dim =256
    # output layer for mean and log variance
    z_mu = Dense(latent_dim)(encoder_outputs)  #remplacer h
    z_log_var = Dense(latent_dim)(encoder_outputs)

def sampling(args):
   batch_size=1
   z_mean, z_log_sigma = args
   epsilon = K.random_normal(shape=(batch_size, latent_dim),
                          mean=0., stddev=1.)
   return z_mean + K.exp(z_log_sigma/2) * epsilon

    z = Lambda(sampling, output_shape=(None,))([z_mu, z_log_var])
    def vae_loss(y_true, y_pred):
     # E[log P(X|z)]
      recon = K.sum(K.binary_crossentropy(y_pred, y_true), axis=-1)
      kl_loss = - 0.5 * K.sum(1 + z_log_var - K.square(z_mean) - 
      K.exp(z_log_var), axis=-1)

      return recon + kl_loss

    decoder_inputs = Input(shape=(None,))
    decoder_emb = Embedding(input_dim=vocab_out_size, output_dim=embedding_dim)
    decoder_lstm = LSTM(units=units, return_sequences=True, return_state=True)
    decoder_lstm_out, _, _ = decoder_lstm(decoder_emb(decoder_inputs), initial_state=encoder_states)
    decoder_d2 = Dense(vocab_out_size, activation="softmax")
    decoder_out = decoder_d2(decoder_lstm_out)
    model = Model([encoder_inputs, decoder_inputs], decoder_out)
    model.compile(optimizer='rmsprop', 
    loss=vae_loss, metrics= 
    ['accuracy'])

我想将表示形式潜在z传递给解码器。我发现的所有示例在解码器中都没有嵌入层。所以，我有关于形状的错误。我应该在哪里确切使用z？ 拜托我需要你的帮忙 谢谢。