vector-quantize-pytorch
vector-quantize-pytorch copied to clipboard
lucidrains
Vector (and Scalar) Quantization, in Pytorch
Hi, It seems like there's a problem when using `soundstream.eval()` due to the RVQ part. Not a big deal but I wanted to let you know about that
Hi, Thanks for this cool work! I couldn't help but notice that a few features used to improve the usage of the codebooks were missing to be an exact implementation...
Hi Lucid, i am working on quantizing CLIP image embeddings with your RQ-VAE. It works pretty well. Next I want to take all learned codebook vectors and add them to...
Hello, First of all, thank you so much for this powerful implementation. I have been researching to train some VQ-VAE to generate faces from FFHQ 128x128 and I always have...
The original VIT-VQGAN paper does not seem to use EMA update for codebook learning since their codebook is unit-normalized vectors. Particularly, to my understanding, EMA update does not quite make...
kmeans and ddp hangs for me. ddp is initialized by pytorch lightning in my case. I have several questions: In https://github.com/lucidrains/vector-quantize-pytorch/blob/master/vector_quantize_pytorch/vector_quantize_pytorch.py#L98 `all_num_samples = all_gather_sizes(local_samples, dim = 0)` should it be...
When using `FSQ` with `[8, 5, 5, 5]` levels, and in `pytorch-lightning` specifying `bfloat16` training, the codebook utilization scratches 50% from below, while when training with `float32` it scratches 100%....
Dear @lucidrains, throughout my experimentations with this wonderful library, I found some weird behaviour when using lower codebook dimensions; ``` # everything okay import torch from vector_quantize_pytorch import VectorQuantize vq...
I can run the README code in a single GPU, but get error when i run the multi GPU distribution training Traceback (most recent call last): File "/vepfs/home/tianbo/sora/test.py", line 77,...
Metadata
Owner
Metadata
Vector (and Scalar) Quantization, in Pytorch