Unofficial implementation of S3VAE with pytorch
This repository is inspired by here
The Moving MNIST dataset contains 10,000 video sequences, each consisting of 20 frames. In each video sequence, two digits move independently around the frame, which has a spatial resolution of 64×64 pixels. The digits frequently intersect with each other and bounce off the edges of the frame.
More details
python click/predict.py generate-moving-mnist -c s3vae_config.yaml
- fix mutual information loss
- edit wandb log name