Tomoya Sawada

The model collapsed after several epochs of training

In the BigGAN paper, they have improved the scores by using bigger batch size and a larger model. I used the batch size of 12, which is the biggest batch...

Could not get good results in ContraD. ## what can be done. - Train with more simpler model. (vs StyleGAN2) - Further hyper-parameter tuning. - Loss function. (taken from original...

U-GAT-IT could not be trained on my env. (Takes too much memory and time.)

H2O Wave

2

# WHAT - add system and training visualization using [H2O Wave](https://h2oai.github.io/wave/) - add `services` in `docker-compose.yml` which runs the wave server. - add `Dockerfile` for H2O Wave - add `h2o_wave`,...

# WHAT - Renew EVERYTHING to my latest programming style. - Retrain all models and update results. ## Changes - Configuration via `hydra`. - Use https://github.com/STomoya/storch instead of writing utilities...