https://github.com/paparazz1/dr-gan
pytorch implement for DR-GAN
https://github.com/paparazz1/dr-gan
frontal-facial-images gan
Last synced: about 1 month ago
JSON representation
pytorch implement for DR-GAN
- Host: GitHub
- URL: https://github.com/paparazz1/dr-gan
- Owner: PaParaZz1
- Created: 2018-09-24T05:46:01.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2019-06-28T01:26:25.000Z (almost 6 years ago)
- Last Synced: 2025-04-01T21:06:35.888Z (2 months ago)
- Topics: frontal-facial-images, gan
- Language: Python
- Size: 46.8 MB
- Stars: 7
- Watchers: 0
- Forks: 0
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# DR-GAN(pytorch implement for DR-GAN)
## paper link
http://cvlab.cse.msu.edu/pdfs/Tran_Yin_Liu_CVPR2017.pdf
## requirements
- python3.6
- pytorch0.3.1
- torchvision
- numpy
- opencv-python
- pillow
## usage
- view option/base_option.py train_option.py test_option.py and revise setting yourself
- train: python train.py
- test: python test.py
- I add some data augment in test.py for experiment comparsion, they are origin, gauss_noise,
gamma_transform, shadow, random color and blur consecutively.
- pretrained model in directory checkpoints
## dataset
I train this model use cfp-dataset, due to dataset size and lack of labeled information, my GAN can't converge very well. If you have
other dataset like Multi-PIE it would be helpful.
## more details
You can read some comments in code or experiment_record.md for more details
**If you have any questions please come up with issue**