wyu-du / gp-vae Goto Github PK

Is this a custom function？ Can provide it?

When I am trying to train the t5-gpave, there is a problem of "zero kld!!!".

Also, the "zero kld!!!" is also in the training of the LSTM-based variational encoder-decoder with GP priors.
Thank you for your help and I am looking forward to hearing from you.

Hi!
Thanks for your great work! I'm working on getting results on another paraphrase dataset under T5 + GP prior setting. I have the following two questions:

• I found that the generation speed is relatively slow due to the inference batch size 1, and something get wrong if I change it. Is there any way to speed up the generation?
• if I want to get a trade-off between quality and diversity, is it suitable to set the scalar to 7 just like it used in the paper for the paraphrasing task?

Hi! I need to do some comparative experiments. Could you please provide the output on the formal style transfer task (GYAFC dataset)?

Great work ! Is there any plan to release the pre-trained model weights ?

请问可以提供其他数据集吗

Thank you for your great work! I am learning VAE recently, your paper have given me great inspiration.

In naive VAE, the KL divergence should be $KL(\mathcal{N}(\mu, \sigma), \mathcal{N}(0,1))$. But when reading your code, I found model/t5/t5_vae.py line 151, you set the prior_logvar as 0. Is there any mistake?

prior_mean = torch.zeros([hidden_states.size(0), posterior_mean.size(-1)]) \
    .to(posterior_mean.dtype).to(posterior_mean.device)
prior_logvar = torch.zeros([hidden_states.size(0), posterior_logvar.size(-1)]) \
      .to(posterior_logvar.dtype).to(posterior_logvar.device)