https://github.com/paparazz1/tp-gan
pytorch implemention for TP-GAN
https://github.com/paparazz1/tp-gan
Last synced: about 2 months ago
JSON representation
pytorch implemention for TP-GAN
- Host: GitHub
- URL: https://github.com/paparazz1/tp-gan
- Owner: PaParaZz1
- Created: 2018-09-18T11:16:50.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2018-09-18T12:04:15.000Z (over 6 years ago)
- Last Synced: 2025-04-01T21:02:55.823Z (3 months ago)
- Language: Python
- Size: 13.7 KB
- Stars: 9
- Watchers: 0
- Forks: 0
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# README
This is a development pytorch version of TP-GAN(Two pathway GAN).
# requires
- python3.6
- pytorch0.3.1
# directory structure
- config: global configuration and parameter
- main: network train and test
- utils: train support logs and functions
- network: (TP-GAN)network architecture
- data_preprocessing: data preprocessing
- data: image and image list
- model: pre-train model, save model, feature_extract_model
# network architecture change
- use WGAN-GP loss replace origin adversarial loss
- use pytorch official resnet18 as feature extract network to calculate identity preserving loss
If you have any problems, please contact with [email protected]