Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"
| Date | Stars |
|---|---|
| 2026-07-30 | 1096 |
| 2026-08-10 | 1095 |
| 2026-09-26 | 1096 |
| 2026-10-14 | 1097 |
| 2026-10-20 | 1097 |
| 2026-10-26 | 1097 |
| 2026-10-29 | 1097 |
| 2026-10-30 | 1098 |
| 2026-11-04 | 1098 |
Today
— stars today
This week
+1 stars this week
This month
+2 stars this month
Momentum
0.0
growth rate 0.09%/day
# DiscoGAN in PyTorch
PyTorch implementation of [Learning to Discover Cross-Domain Relations with Generative Adversarial Networks](https://arxiv.org/abs/1703.05192).
<img src="./assets/model.png" width="80%">
**\* All samples in README.md are genearted by neural network except the first image for each row.**
\* Network structure is slightly diffferent ([here](https://github.com/carpedm20/DiscoGAN-pytorch/blob/master/models.py#L13-L32)) from the author's [code](https://github.com/SKTBrain/DiscoGAN/blob/master/discogan/model.py#L69-L125).
## Requirements
- Python 2.7
- [Pillow](https://pillow.readthedocs.io/en/4.0.x/)
- [tqdm](https://github.com/tqdm/tqdm)
- [PyTorch](https://github.com/pytorch/pytorch)
- [torch-vision](https://github.com/pytorch/vision)
## Usage
First download datasets (from [pix2pix](https://github.com/phillipi/pix2pix)) with:
$ bash ./data/download_dataset.sh dataset_name
- `facades`: 400 images from [CMP Facades dataset](http://cmp.felk.cvut.cz/~tylecr1/facade/).
- `cityscapes`: 2975 images from the [Cityscapes training set](https://www.cityscapes-dataset.com/).
- `maps`: 1096 training images scraped from Google Maps
- `edges2shoes`: 50k training images from [UT Zappos50K dataset](http://vision.cs.utexas.edu/projects/finegrained/utzap50k/).
- `edges2handbags`: 137K Amazon Handbag images from [iGAN project](https://github.com/junyanz/iGAN).
or you can use your own dataset by placing images like:
data
├── YOUR_DATASET_NAME
│ ├── A
│ | ├── xxx.jpg (name doesn't matter)
│ | ├── yyy.jpg
│ | └── ...
│ └── B
│ ├── zzz.jpg
│ ├── www.jpg
│ └── ...
└── download_dataset.sh
**All images in each dataset should have same size** like using [imagemagick](https://www.imagemagick.org/script/index.php):
# for Ubuntu
$ sudo apt-get install imagemagick
$ mogrify -resize 256x256! -quality 100 -path YOUR_DATASET_NAME/A/*.jpg
$ mogrify -resize 256x256! -quality 100 -path YOUR_DATASET_NAME/B/*.jpg
# for Mac
$ brew install imagemagick
$ mogrify -resize 256x256! -quality 100 -path YOUR_DATASET_NAME/A/*.jpg
$ mogrify -resize 256x256! -quality 100 -path YOUR_DATASET_NAME/B/*.jpg
# for scale and center crop
$ mogrify -resize 256x256^ -gravity center -crop 256x256+0+0 -quality 100 -path ../A/*.jpg
To train a model:
$ python main.py --dataset=edges2shoes --num_gpu=1
$ python main.py --dataset=YOUR_DATASET_NAME --num_gpu=4
To test a model (use your `load_path`):
$ python main.py --dataset=edges2handbags --load_path=logs/edges2handbags_2017-03-18_10-55-37 --num_gpu=0 --is_train=False
## Results
### 1. Toy dataset
Result of samples from 2-dimensional Gaussian mixture models. [IPython notebook](./notebooks/DiscoGAN.ipynb)
**# iteration: 0**:
<img src="./assets/toy_before.png" width="30%">
**# iteration: 10000**:
<img src="./assets/toy_after.png" width="30%">
### 2. Shoes2handbags dataset
**# iteration: 11200**:
`x_A` -> `G_AB(x_A)` -> `G_BA(G_AB(x_A))` (shoe -> handbag -> shoe)
<img src="assets/shoes2handbags_valid_x_B.png" width="30%"> <img src="assets/shoes2handbags_x_BA_11200.png" width="30%"> <img src="assets/shoes2handbags_x_BAB_11200.png" width="30%">
`x_B` -> `G_BA(x_B)` -> `G_AB(G_BA(x_B))` (handbag -> shoe -> handbag)
<img src="assets/shoes2handbags_valid_x_A.png" width="30%"> <img src="assets/shoes2handbags_x_AB_11200.png" width="30%"> <img src="assets/shoes2handbags_x_ABA_11200.png" width="30%">
`x_A` -> `G_AB(x_A)` -> `G_BA(G_AB(x_A))` -> `G_AB(G_BA(G_AB(x_A)))` -> `G_BA(G_AB(G_BA(G_AB(x_A))))` -> ...
<img src="assets/shoes2handbags_repetitive_0_x_A_0.png" width="13%"> <img src="assets/shoes2handbags_repetitive_0_x_A_1.png" width="13%"> <img src="assets/shoes2handbags_repetitive_0_x_A_2.png" width="13%"> <img src="assets/shoes2handbags_repetitive_0_x_A_3.png" width="13%"> <img src="assets/shoes2handbags_repetitive_0_x_A_4.png" width="13%"> <img src="assets/shoeExcerpt of 8,527 characters
Read on GitHub
Taehoon · United States
45
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c86e7eeb6aeefa22, topic:pytorch
matched fp:c86e7eeb6aeefa22, topic:gan