Hao Phung

How many epochs required for training?

2

When digging in your code, I found that training is based on a number of total iterations (let's call `max_steps`). Based on your codes in `experiment.py`, it is computed as...

Training autoenc and Training latent DDM

4

Might I ask a stupid question that what is the difference between training autoenc and training latent DDM? As far as I understand, I suppose these two are trained at...

Have you tried different output channels for single projection and dense projection? Particularly, you used the same hidden channels and output channels for single mlp and dense mlp in the...

First of all, I'd like to thank you for your great work. I have adopted your BoW implementation to my method and `mu_min_dist` in `BoWExtractor` class got inf value after...

Training setting on Cifar

1

 Training setting on repo is different from paper: `nz=100`, `z_emb_dim=256`. Could you please tell me what is the correct setting? Thank you very much!

Thank for your great work! However, I got NAN loss issue when training with your provided code! As I saw in the paper, you also have an additional GAN loss...