sony / sqvae

Pytorch implementation of stochastically quantized variational autoencoder (SQ-VAE)
Apache License 2.0
179 stars 21 forks source link

Generative model #2

Closed VuongLong closed 2 years ago

VuongLong commented 2 years ago

Thank you for the implementation!

I could not find the code/models for samples generated with a prior learned with PixelCNN.

Could you kindly share that? Thanks!

ytakida commented 2 years ago

Thank you for your interest in our work! and Sorry for the late response.

We're sorry that we are not planning to upload code and models for prior models. We refer to the following repositories for the implementation. https://github.com/anordertoreclaim/PixelCNN https://github.com/rosinality/vq-vae-2-pytorch

Since we focused on comparisons among main VAE models (SQ-VAE and other conventional VQ-VAE models) under fair conditions, we used a simple prior model rather than sophisticated ones.