pytorch-vqvae

pytorch-vqvae copied to clipboard

Codebook embedding does not update

4

I found `ctx.needs_input_grad[1]` is `False` during training VQ-VAE. Is this correct, and does it mean the embedding of the codebook does not update during training? https://github.com/ritheshkumar95/pytorch-vqvae/blob/8d123c0d043bebc8734d37785dd13dd20e7e5e0e/functions.py#L53

zhxgj

I am just wondering why your let train_loader shuffle = False and test_loader shuffle=True? Should it be vice versa?

xiaodaxia007

Hi, I have trained the VQVAE network on my own dataset comprise of 10,000 images of 64×64 pixels without any labels. In order to train PixelCNN network, I faked some...

ZhanYangen

How to generate images from the PixelCNN?

7

The PixelCNN learn to model the prior q(z) in the paper and the code. For any given classes/labels, PixelCNN should model their prior q(z), as shown in the code https://github.com/ritheshkumar95/pytorch-vqvae/blob/8d123c0d043bebc8734d37785dd13dd20e7e5e0e/modules.py#L262...

Hanzy1996

I think you forgot to set train/eval mode in your train/test function. Since `VectorQuantizedVAE` contains batchnorm that is required to obtain correct results. You do seem to set it in...

y0ast

Dear [ritheshkumar95](https://github.com/ritheshkumar95), We want to express our gratitude for your implementation of the pytorch VQ-VAE. Thanks to your work, we were able to develop and publish our own model, TVQ-VAE,...

yjyoo3312

Example for raw audio

4

Hello, and thanks for the code! I want to replicate the audio results from the paper, but the DeepMind repo does not have a VQ-VAE example for audio (see https://github.com/google-deepmind/sonnet/issues/141...

mm3509

i want know the code of loss: log_px = nll.mean().item() - np.log(128) + kl_d.item() in that code of loss , the 128 of 'np.log(128)' is value of Z_DIM ?

WenBingo

Primarily: 1. add default values for "data-folder" and "dataset". 2. correct the error of not using CUDA when it is available. Secondary: correct the wrong dimension of transform for 'mnist',...

Roller44

Question ragarding z_q_x_st and z_q_x of class VectorQuantizedVAE in modules.py

1

Thanks for your great work! I can't figure out the difference between variable (z_ q_ x_ st) and variable (z_q_x) in forward() of class VectorQuantizedVAE.  I debug the code...

RipeMangoBox