https://github.com/sslotin/ganime

Tiny project: dual Wasserstein GAN for anime
https://github.com/sslotin/ganime

anime deep-learning dualgan faces gans machine-learning pytorch wgan-gp

Last synced: 2 months ago
JSON representation

Tiny project: dual Wasserstein GAN for anime

• Host: GitHub
• URL: https://github.com/sslotin/ganime
• Owner: sslotin
• Created: 2018-05-23T22:56:12.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2018-06-24T17:00:16.000Z (about 8 years ago)
• Last Synced: 2025-12-30T17:36:24.376Z (6 months ago)
• Topics: anime, deep-learning, dualgan, faces, gans, machine-learning, pytorch, wgan-gp
• Language: Python
• Homepage:
• Size: 11.7 KB
• Stars: 2
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# GANime

Implementation of Dual Wasserstein GAN for face2anime.

(https://arxiv.org/pdf/1704.02510.pdf)

(https://arxiv.org/pdf/1704.00028.pdf)

Works with 64 by 64 pictures of I don't remember which datasets that I found on google.

TODO: make train.py be device-agnostic.

TODO: log losses and make some better visualizations.

UPD (june 15): managed to get gtx 1080 for a few days and currently it is training.