subinium / VQVAE

Unofficial Pytorch implementation of Neural Discrete Representation Learning (2017) : https://arxiv.org/abs/1711.00937

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Pytorch VQ-VAE Implementation

Unofficial Pytorch implementation of Neural Discrete Representation Learning (2017)

Based on zalandoresearch/pytorch-vq-vae repository.

Install

$ pip install -r requirements.txt

Usage

You can experiment with CIFAR-10 data by running the following command:

python train.py

In the case of hyperparameters, you can experiment by tuning in config.json.

Experiments (TBD)

To Do

  • VectorQuantize EMA ver.
  • Warm Start (Save model & Load pre-trained model)
  • Inference (unseen random size image)
  • Visualization for Interpretability (Interactive Mode)

Contact

If you have any question about the code, feel free to email me at subinium@gmail.com.

ezoic increase your site revenue

About

Unofficial Pytorch implementation of Neural Discrete Representation Learning (2017) : https://arxiv.org/abs/1711.00937

License:Apache License 2.0


Languages

Language:Python 100.0%