diff options
| author | junyanz <junyanz@berkeley.edu> | 2017-04-18 04:12:22 -0700 |
|---|---|---|
| committer | junyanz <junyanz@berkeley.edu> | 2017-04-18 04:12:22 -0700 |
| commit | b4a405253e74d1812ce1067d8127d6fd7fc0352f (patch) | |
| tree | ef06af6c8dfcd84fe57ddc58f2434f5cf3b68838 /README.md | |
| parent | f2fba75f4d3be32c45e7738ecaca1e6bd64015dd (diff) | |
update README
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 15 |
1 files changed, 9 insertions, 6 deletions
@@ -1,10 +1,12 @@ <img src='imgs/horse2zebra.gif' align="right" width=384> -<br><br><br> +<br> # CycleGAN and pix2pix in PyTorch -This is our ongoing PyTorch implementation for both unpaired and paired image-to-image translation. Check out the original [CycleGAN Torch](https://github.com/junyanz/CycleGAN) and [pix2pix Torch](https://github.com/phillipi/pix2pix) if you would like to reproduce the exact same results in the paper. The code was written by [Jun-Yan Zhu](https://github.com/junyanz) and [Taesung Park](https://github.com/taesung89). +This is our ongoing PyTorch implementation for both unpaired and paired image-to-image translation. Check out the original [CycleGAN Torch](https://github.com/junyanz/CycleGAN) and [pix2pix Torch](https://github.com/phillipi/pix2pix) if you would like to reproduce the exact same results in the paper. + +The code was written by [Jun-Yan Zhu](https://github.com/junyanz) and [Taesung Park](https://github.com/taesung89). #### CycleGAN: [[Project]](https://junyanz.github.io/CycleGAN/) [[Paper]](https://arxiv.org/pdf/1703.10593.pdf) [[Torch]](https://github.com/junyanz/CycleGAN) @@ -129,10 +131,11 @@ python datasets/combine_A_and_B.py --fold_A /path/to/data/A --fold_B /path/to/da This will combine each pair of images (A,B) into a single image file, ready for training. ## TODO -- add Unet architecture -- add one-direction test model -- fully test instance normalization from [fast-neural-style project](https://github.com/darkstar112358/fast-neural-style) -- fully test CPU mode and multi-GPU mode +- add reflection and other padding layers. +- add one-direction test model. +- fully test Unet architecture. +- fully test instance normalization layer from [fast-neural-style project](https://github.com/darkstar112358/fast-neural-style). +- fully test CPU mode and multi-GPU mode. ## Related Projects: [CycleGAN](https://github.com/junyanz/CycleGAN): Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks |