ComboGAN
This is our ongoing PyTorch implementation for ComboGAN. Code was written by Asha Anoosheh (built upon CycleGAN)
[ComboGAN Paper]
If you use this code for your research, please cite:
ComboGAN: Unrestrained Scalability for Image Domain Translation Asha Anoosheh, Eirikur Augustsson, Radu Timofte, Luc van Gool In Arxiv, 2017.
Prerequisites
- Linux or macOS
- Python 3
- CPU or NVIDIA GPU + CUDA CuDNN
Getting Started
Installation
- Install PyTorch and dependencies from http://pytorch.org
- Install Torch vision from the source.
git clone https://github.com/pytorch/vision
cd vision
python setup.py install
pip install visdom
pip install dominate
- Clone this repo:
git clone https://github.com/AAnoosheh/ComboGAN.git
cd ComboGAN
ComboGAN training
Our ready datasets can be downloaded using ./datasets/download_dataset.sh
.
A pretrained model for the 14-painters dataset can be found HERE. Place under ./checkpoints/ and test using the instructions below, with args --name paint14_pretrained --dataroot ./datasets/painters_14 --n_domains 14 --which_epoch 1150.
Example running scripts can be found in the scripts directory.
- Train a model:
python train.py --name
--dataroot ./datasets/
--n_domains
--niter
--niter_decay
Checkpoints will be saved by default to ./checkpoints/
- Fine-tuning/Resume training:
python train.py --continue_train --which_epoch
--name
--dataroot ./datasets/
--n_domains
--niter
--niter_decay
- Test the model:
python test.py --phase test --name
--dataroot ./datasets/
--n_domains
--which_epoch
--serial_test
The test results will be saved to a html file here: ./results/
.
Training/Testing Details
- Flags: see
options/train_options.pyfor training-specific flags; seeoptions/test_options.pyfor test-specific flags; and seeoptions/base_options.pyfor all common flags. - Dataset format: The desired data directory (provided by
--dataroot) should contain subfolders of the formtrain*/andtest*/, and they are loaded in alphabetical order. (Note that a folder named train10 would be loaded before train2, and thus all checkpoints and results would be ordered accordingly.) - CPU/GPU (default
--gpu_ids 0): set--gpu_ids -1to use CPU mode; set--gpu_ids 0,1,2for multi-GPU mode. You need a large batch size (e.g.--batchSize 32) to benefit from multiple GPUs. - Visualization: during training, the current results and loss plots can be viewed using two methods. First, if you set
--display_id> 0, the results and loss plot will appear on a local graphics web server launched by visdom. To do this, you should havevisdominstalled and a server running by the commandpython -m visdom.server. The default server URL ishttp://localhost:8097.display_idcorresponds to the window ID that is displayed on thevisdomserver. Thevisdomdisplay functionality is turned on by default. To avoid the extra overhead of communicating withvisdomset--display_id 0. Secondly, the intermediate results are also saved to./checkpoints/. To avoid this, set the/web/index.html --no_htmlflag. - Preprocessing: images can be resized and cropped in different ways using
--resize_or_cropoption. The default option'resize_and_crop'resizes the image to be of size(opt.loadSize, opt.loadSize)and does a random crop of size(opt.fineSize, opt.fineSize).'crop'skips the resizing step and only performs random cropping.'scale_width'resizes the image to have widthopt.fineSizewhile keeping the aspect ratio.'scale_width_and_crop'first resizes the image to have widthopt.loadSizeand then does random cropping of size(opt.fineSize, opt.fineSize).
NOTE: one should not expect ComboGAN to work on just any combination of input and output datasets (e.g. dogs<->houses). We find it works better if two datasets share similar visual content. For example, landscape painting<->landscape photographs works much better than portrait painting <-> landscape photographs.
90 Dec 8, 2022
121 Dec 17, 2022
172 Dec 12, 2022
111 Dec 8, 2022
76 Jan 7, 2023
13 Nov 19, 2022
556 Jan 4, 2023
616 Jan 6, 2023
520 Dec 30, 2022
6.9k Jan 3, 2023
119 Nov 24, 2022
1.4k Jan 1, 2023
360 Dec 10, 2022
9.2k Jan 2, 2023
0 Jul 13, 2021
8 Nov 21, 2022
157 Dec 11, 2022
6 Mar 17, 2022