Project Report link: final_project.pdf

1. To train the VQVAE with default arguments as discussed in the report, execute:

python vqvae.py --data-folder /tmp/miniimagenet --output-folder models/vqvae

2. To train the PixelCNN prior on the latents, execute:

python pixelcnn_prior.py --data-folder /tmp/miniimagenet --model models/vqvae --output-folder models/pixelcnn_prior

1. MNIST
2. FashionMNIST
3. CIFAR10
4. Mini-ImageNet

1. Atari 2600 - Boxing (OpenAI Gym) code

Top 4 rows are Original Images. Bottom 4 rows are Reconstructions.

1. We noticed that implementing our own VectorQuantization PyTorch function speeded-up training of VQ-VAE by nearly 3x. The slower, but simpler code is in this commit.
2. We added some basic tests for the vector quantization functions (based on pytest). To run these tests

py.test . -vv

1. Rithesh Kumar
2. Tristan Deleu
3. Evan Racah