multimodal-vae-public

multimodal-vae-public copied to clipboard

Not getting similar results as reported in the paper

4

Code is not working for celeba. I am not able to obtain the results as reported in the paper. The image reconstruction and random sample generation both are of worse...

ry85

Hi, For MVAE19, I see that 18 modalities are in the form of text. Would it be possible to use high dimensional data (approx 1x1000) as an input modality? For...

kunwooch

Hi, could you upload the implementation of loglike.py for the project? Thank you.

Michael-Pan95

I was looking at the implementation of prior_expert and found the following line : logvar = Variable(torch.log(torch.ones(size))) If it's going to represent N(0,1), logvar should be 0 since variance is...

ankit1089sny