我一直在尝试创建 LSTM VAE 来重建 Tensorflow 上的多元时间序列数据。首先，我尝试调整（更改为功能 API，更改层）此处采用的方法，并得出以下代码：
input_shape = 13
latent_dim = 2
prior = tfd.Independent(tfd.Normal(loc=tf.zeros(latent_dim), scale=1), reinterpreted_batch_ndims=1)
input_enc = Input(shape=[512, input_shape])
lstm1 = LSTM(latent_dim * 16, return_sequences=True)(input_enc)
lstm2 = LSTM(latent_dim * 8, return_sequences=True)(lstm1)
lstm3 = LSTM(latent_dim * 4, return_sequences=True)(lstm2)
lstm4 = LSTM(latent_dim * 2, return_sequences=True)(lstm3)
lstm5 = LSTM(latent_dim, return_sequences=True)(lstm4)
lat = Dense(tfpl.MultivariateNormalTriL.params_size(latent_dim))(lstm5)
reg = tfpl.MultivariateNormalTriL(latent_dim, activity_regularizer= tfpl.KLDivergenceRegularizer(prior, weight=1.0))(lat)
lstm6 = LSTM(latent_dim, return_sequences=True)(reg)
lstm7 = LSTM(latent_dim * 2, return_sequences=True)(lstm6)
lstm8 = LSTM(latent_dim * 4, return_sequences=True)(lstm7)
lstm9 = LSTM(latent_dim …