VITA-Group/TransGAN
VITA-Group/TransGAN has 1,694 GitHub stars and 202 forks. GitHot measured 0 stars in 24 hours, 0 in 7 days, and +1 in 15 days. Last checked 2026-11-20 21:16 UTC. Last push 2022-11-03.
計測したスター増加
- 24時間
- 0
- 7日間
- 0
- 15日間
- +1
- 1か月
- 履歴を収集中
期間ごとの純増数です。期間は重複しており、日別の値ではありません。未計測の値は空欄です。スター数は注目度の指標であり、品質の保証ではありません。
概要
[NeurIPS‘2021] "TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up", Yifan Jiang, Shiyu Chang, Zhangyang Wang
機械学習README.md
オリジナルTransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
Code used for TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up.
Implementation
- checkpoint gradient using torch.utils.checkpoint
- 16bit precision training
- Distributed Training (Faster!)
- IS/FID Evaluation
- Gradient Accumulation
- Stronger Data Augmentation
- Self-Modulation
Guidance
Cifar training script
python exp/cifar_train.py
I disabled the evaluation during training job as it causes strange bug. Please launch another evaluation job simultaneously by copying the path to test script.
Cifar test
First download the cifar checkpoint and put it on ./cifar_checkpoint. Then run the following script.
python exp/cifar_test.py
Main Pipeline

Representative Visual Results

README waits for updated
Acknowledgement
Codebase from AutoGAN, pytorch-image-models
Citation
if you find this repo is helpful, please cite
@article{jiang2021transgan,
title={Transgan: Two pure transformers can make one strong gan, and that can scale up},
author={Jiang, Yifan and Chang, Shiyu and Wang, Zhangyang},
journal={Advances in Neural Information Processing Systems},
volume={34},
year={2021}
}