tra
transganformer
pypi i transganformer
tra

transganformer

Implementation of TransGanFormer, an all-attention GAN that combines the finding from the recent GanFormer and TransGan paper

by Phil Wang

0.0.17 (see all)License:MIT
pypi i transganformer
Readme

TransGanFormer (wip)

Implementation of TransGanFormer, an all-attention GAN that combines the finding from the recent GansFormer and TransGan paper. It will also contain a bunch of tricks I have picked up building transformers and GANs for the last year or so, including efficient linear attention and pixel level attention.

Install

$ pip install transganformer

Usage

$ transganformer --data ./path/to/data

Citations

@misc{jiang2021transgan,
    title   = {TransGAN: Two Transformers Can Make One Strong GAN}, 
    author  = {Yifan Jiang and Shiyu Chang and Zhangyang Wang},
    year    = {2021},
    eprint  = {2102.07074},
    archivePrefix = {arXiv},
    primaryClass = {cs.CV}
}
@misc{hudson2021generative,
    title   = {Generative Adversarial Transformers}, 
    author  = {Drew A. Hudson and C. Lawrence Zitnick},
    year    = {2021},
    eprint  = {2103.01209},
    archivePrefix = {arXiv},
    primaryClass = {cs.CV}
}

GitHub Stars

130

LAST COMMIT

1yr ago

MAINTAINERS

1

CONTRIBUTORS

1

OPEN ISSUES

5

OPEN PRs

0
VersionTagPublished
0.0.17
1yr ago
0.0.16
1yr ago
0.0.15
1yr ago
0.0.14
1yr ago
No alternatives found
No tutorials found
Add a tutorial