rosinality/vq-vae-2-pytorch
rosinality/vq-vae-2-pytorch has 1,807 GitHub stars and 279 forks. GitHot measured 0 stars in 24 hours, 0 in 7 days, and +1 in 15 days. Last checked 2026-11-19 04:58 UTC. Last push 2023-02-15.
측정된 스타 증가
- in 24h
- 0
- in 7 days
- 0
- in 15 days
- +1
- in 1 month
- 업데이트 지연
서로 겹치는 기간의 순증가량이며 일별 합계가 아닙니다. 측정값이 없으면 비워 둡니다. 스타는 관심도를 나타내며 품질을 보장하지 않습니다.
소개
Implementation of Generating Diverse High-Fidelity Images with VQ-VAE-2 in PyTorch
머신러닝README.md
Originalvq-vae-2-pytorch
Implementation of Generating Diverse High-Fidelity Images with VQ-VAE-2 in PyTorch
Update
- 2020-06-01
train_vqvae.py and vqvae.py now supports distributed training. You can use --n_gpu [NUM_GPUS] arguments for train_vqvae.py to use [NUM_GPUS] during training.
Requisite
- Python >= 3.6
- PyTorch >= 1.1
- lmdb (for storing extracted codes)
Checkpoint of VQ-VAE pretrained on FFHQ
Usage
Currently supports 256px (top/bottom hierarchical prior)
- Stage 1 (VQ-VAE)
python train_vqvae.py [DATASET PATH]
If you use FFHQ, I highly recommends to preprocess images. (resize and convert to jpeg)
- Extract codes for stage 2 training
python extract_code.py --ckpt checkpoint/[VQ-VAE CHECKPOINT] --name [LMDB NAME] [DATASET PATH]
- Stage 2 (PixelSNAIL)
python train_pixelsnail.py [LMDB NAME]
Maybe it is better to use larger PixelSNAIL model. Currently model size is reduced due to GPU constraints.
Sample
Stage 1
Note: This is a training sample
