From 06ff1058ad85bef386130eaa184c3d60e86d2fee Mon Sep 17 00:00:00 2001 From: junyanz Date: Tue, 18 Apr 2017 04:01:07 -0700 Subject: update README --- README.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 6b5b44b..7e45f3c 100644 --- a/README.md +++ b/README.md @@ -7,14 +7,16 @@ 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 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) +#### CycleGAN: [[Project]](https://junyanz.github.io/CycleGAN/) [[Paper]](https://arxiv.org/pdf/1703.10593.pdf) [[Torch]](https://github.com/junyanz/CycleGAN) -### Pix2pix: [[Project]](https://phillipi.github.io/pix2pix/) [[Paper]](https://arxiv.org/pdf/1611.07004v1.pdf) [[Torch]](https://github.com/phillipi/pix2pix) +#### Pix2pix: [[Project]](https://phillipi.github.io/pix2pix/) [[Paper]](https://arxiv.org/pdf/1611.07004v1.pdf) [[Torch]](https://github.com/phillipi/pix2pix) -### EdgesCats: [[Demo]](https://affinelayer.com/pixsrv/) [[Twitter]](https://twitter.com/search?vertical=default&q=pix2pix&src=typd) [[pix2pix-tensorflow]](https://github.com/affinelayer/pix2pix-tensorflow) +#### [[EdgesCats Demo]](https://affinelayer.com/pixsrv/) [[pix2pix-tensorflow]](https://github.com/affinelayer/pix2pix-tensorflow) +Written by [Christopher Hesse](https://twitter.com/christophrhesse) + If you use this code for your research, please cite: -- cgit v1.2.3-70-g09d2 From 3310304db45880c63fb7b221e30eeb67298b2682 Mon Sep 17 00:00:00 2001 From: junyanz Date: Tue, 18 Apr 2017 04:01:52 -0700 Subject: update README --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 7e45f3c..52a8497 100644 --- a/README.md +++ b/README.md @@ -8,11 +8,11 @@ This is our ongoing PyTorch implementation for both unpaired and paired image-to #### CycleGAN: [[Project]](https://junyanz.github.io/CycleGAN/) [[Paper]](https://arxiv.org/pdf/1703.10593.pdf) [[Torch]](https://github.com/junyanz/CycleGAN) - + #### Pix2pix: [[Project]](https://phillipi.github.io/pix2pix/) [[Paper]](https://arxiv.org/pdf/1611.07004v1.pdf) [[Torch]](https://github.com/phillipi/pix2pix) - + #### [[EdgesCats Demo]](https://affinelayer.com/pixsrv/) [[pix2pix-tensorflow]](https://github.com/affinelayer/pix2pix-tensorflow) Written by [Christopher Hesse](https://twitter.com/christophrhesse) -- cgit v1.2.3-70-g09d2 From f2fba75f4d3be32c45e7738ecaca1e6bd64015dd Mon Sep 17 00:00:00 2001 From: junyanz Date: Tue, 18 Apr 2017 04:06:37 -0700 Subject: update README.md --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 52a8497..2d10583 100644 --- a/README.md +++ b/README.md @@ -4,7 +4,7 @@ # 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 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) @@ -34,7 +34,7 @@ In CVPR 2017. ## Prerequisites - Linux or OSX. -- Python 2 and 3. +- Python 2 or Python 3. - CPU or NVIDIA GPU + CUDA CuDNN. ## Getting Started @@ -89,7 +89,7 @@ More example scripts can be found at `scripts` directory. ### CycleGAN Datasets Download the CycleGAN datasets using the following script: ```bash -bash ./datasets/download_CycleGAN_dataset.sh dataset_name +bash ./datasets/download_cyclegan_dataset.sh dataset_name ``` - `facades`: 400 images from the [CMP Facades dataset](http://cmp.felk.cvut.cz/~tylecr1/facade/). - `cityscapes`: 2975 images from the [Cityscapes training set](https://www.cityscapes-dataset.com/). -- cgit v1.2.3-70-g09d2 From b4a405253e74d1812ce1067d8127d6fd7fc0352f Mon Sep 17 00:00:00 2001 From: junyanz Date: Tue, 18 Apr 2017 04:12:22 -0700 Subject: update README --- README.md | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 2d10583..1be7afa 100644 --- a/README.md +++ b/README.md @@ -1,10 +1,12 @@ -


+
# 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 -- cgit v1.2.3-70-g09d2