Pytorch implementation for our MSGAN (Miss-GAN). We propose a simple yet effective mode seeking regularization term that can be applied to arbitrary conditional generative adversarial networks in different tasks to alleviate the mode collapse issue and improve the diversity.
Contact: Qi Mao ([email protected]), Hsin-Ying Lee ([email protected]), and Hung-Yu Tseng ([email protected])
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
Qi Mao*, Hsin-Ying Lee*, Hung-Yu Tseng*, Siwei Ma, and Ming-Hsuan Yang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (* equal contribution)
[arxiv]
If you find MSGAN useful in your research, please consider citing:
@inproceedings{MSGAN,
author = {Mao, Qi and Lee, Hsin-Ying and Tseng, Hung-Yu and Ma, Siwei and Yang, Ming-Hsuan},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},
title = {Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis},
year = {2019}
}
- Python 3.5 or Python 3.6
- Pytorch 0.4.0 and torchvision (https://pytorch.org/)
- TensorboardX
- Tensorflow (for tensorboard usage)
- Clone this repo:
git clone https://github.com/HelenMao/MSGAN.git
Download datasets for each task into the dataset folder
mkdir datasets
- Dataset: CIFAR-10
- Baseline: DCGAN
cd MSGAN/DCGAN-Mode-Seeking
python train.py --dataroot ./datasets/Cifar10
- Paired Data: facades and maps
- Baseline: Pix2Pix
You can download the facades and maps datasets from the BicycleGAN [Github Project].
We employ the network architecture of the BicycleGAN and follow the training process of Pix2Pix.
cd MSGAN/Pix2Pix-Mode-Seeking
python train.py --dataroot ./datasets/facades
- Unpaired Data: Yosemite (summer <-> winter) and Cat2Dog (cat <-> dog)
- Baseline: DRIT
You can download the datasets from the DRIT [Github Project].
Specify --concat 0
for Cat2Dog to handle large shape variation translation
cd MSGAN/DRIT-Mode-Seeking
python train.py --dataroot ./datasets/cat2dog
- Dataset: CUB-200-2011
- Baseline: StackGAN
You can download the datasets from the StackGAN [Github Project].
cd MSGAN/StackGAN -Mode-Seeking
python main.py --cfg cfg/birds_3stages.yml
- DCGAN-Mode-Seeking
- Pix2Pix-Mode-Seeking for facades and maps
- DRIT-Mode-Seeking for Yosemite and Cat2dog
- StackGAN -Mode-Seeking
Download and save them into
./models/
For Pix2Pix, DRIT, and StackGAN , please follow the instructions of corresponding github projects of the baseline frameworks for more evaluation details.
DCGAN-Mode-Seeking
python test.py --dataroot ./datasets/Cifar10 --resume ./models/DCGAN-Mode-Seeking/00199.pth
Pix2Pix-Mode-Seeking
python test.py --dataroot ./datasets/facades --checkpoints_dir ./models/Pix2Pix-Mode-Seeking/facades --epoch 400
python test.py --dataroot ./datasets/maps --checkpoints_dir ./models/Pix2Pix-Mode-Seeking/maps --epoch 400
DRIT-Mode-Seeking
python test.py --dataroot ./datasets/yosemite --resume ./models/DRIT-Mode-Seeking/yosemite/01200.pth --concat 1
python test.py --dataroot ./datasets/cat2dog --resume ./models/DRIT-Mode-Seeking/cat2dog/01999.pth --concat 0
StackGAN -Mode-Seeking
python main.py --cfg cfg/eval_birds.yml
- DCGAN [Paper]
- Pix2Pix and BicycleGAN [Github Project]
- DRIT [Github Project]
- StackGAN [Github Project]
- FID [Github Project]
- LPIPS [Github Project]
- NDB and JSD [Github Project]