Pytorch-CycleGAN-p2c

A personal project repository based on Pytorch-CycleGAN by aitorzip(https://github.com/aitorzip/PyTorch-CycleGAN).

Prerequisites

Code is intended to work with Python 3.6.x, it hasn't been tested with previous versions. Code is intended to work with torch 1.10.x.

Visdom

To plot loss graphs and draw images in a nice web browser view

pip3 install visdom

Training

1. Setup the dataset

First, you will need to download and setup a dataset. The easiest way is to use one of the already existing datasets on UC Berkeley's repository:

./ download_dataset <dataset_name>

Valid <dataset_name> are: apple2orange, summer2winter_yosemite, horse2zebra, monet2photo, cezanne2photo, ukiyoe2photo, vangogh2photo, maps, cityscapes, facades, iphone2dslr_flower, ae_photos

Alternatively you can build your own dataset by setting up the following directory structure:

.
├── datasets                   
|   ├── <dataset_name>         # i.e. brucewayne2batman
|   |   ├── train              # Training
|   |   |   ├── A              # Contains domain A images (i.e. Bruce Wayne)
|   |   |   └── B              # Contains domain B images (i.e. Batman)
|   |   └── test               # Testing
|   |   |   ├── A              # Contains domain A images (i.e. Bruce Wayne)
|   |   |   └── B              # Contains domain B images (i.e. Batman)

2. Train!

python train.py --dataroot datasets/<dataset_name>/ --cuda

This command will start a training session using the images under the dataroot/train directory with the hyperparameters that showed best results according to CycleGAN authors. You are free to change those hyperparameters, see python train.py --help for a description of those.

Both generators and discriminators weights will be saved under the output directory.

If you don't own a GPU remove the --cuda option, although I advise you to get one!

You can also view the training progress as well as live output images by running python3 -m visdom in another terminal and opening http://localhost:8097/ in your favourite web browser. This should generate training loss progress as shown below (default params, horse2zebra dataset):

Testing

python test.py --dataroot datasets/<dataset_name>/ --cuda

This command will take the images under the dataroot/test directory, run them through the generators and save the output under the output/A and output/B directories. As with train, some parameters like the weights to load, can be tweaked, see python test --help for more information.

License

This project is licensed under the GPL v3 License - see the LICENSE.md file for details

Acknowledgments

Code is based on Pytorch-CycleGAN. All credit goes to the authors of CycleGAN, Zhu, Jun-Yan and Park, Taesung and Isola, Phillip and Efros, Alexei A.

averyyy / pytorch-cyclegan-p2c Goto Github PK