Skip to content
Proyectos

ritheshkumar95/pytorch-vqvae has 955 GitHub stars and 140 forks. Star changes are not measured yet. Last checked 2026-11-14 08:38 UTC. Last push 2023-07-12.

Cómo se miden estas cifras

Crecimiento de estrellas medido

in 24h
Recopilando historial
in 7 days
Recopilando historial
in 15 days
Recopilando historial
in 1 month
Recopilando historial

Cambios netos en períodos que se solapan, no totales diarios. Los datos no disponibles se dejan en blanco. Las estrellas indican interés, no calidad.

Acerca de

Vector Quantized VAEs - PyTorch Implementation

Aprendizaje automático

README.md

Original

Reproducing Neural Discrete Representation Learning

Course Project for IFT 6135 - Representation Learning

Project Report link: final_project.pdf

Instructions

  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
  1. 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

Datasets Tested

Image

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

Video

  1. Atari 2600 - Boxing (OpenAI Gym) code

Reconstructions from VQ-VAE

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

MNIST

png

Fashion MNIST

png

Class-conditional samples from VQVAE with PixelCNN prior on the latents

MNIST

png

Fashion MNIST

png

Comments

  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

Authors

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

Explorar proyectos relacionados