New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Progressive Growing of GANs for Improved Quality, Stability, and Variation #475

Open

icoxfog417 opened this issue Oct 28, 2017 · 3 comments

Labels

CNN ComputerVision

Member

icoxfog417 commented Oct 28, 2017

一言でいうと

GANによる画像生成で、高解像度の生成を実現する新しい学習方法を提案。最初は低解像度・少ないレイヤで学習していき、徐々に高解像度・深いネットワークにしていく。

論文リンク

http://research.nvidia.com/publication/2017-10_Progressive-Growing-of

著者/所属機関

Tero Karras
Timo Aila
Samuli Laine
Jaakko Lehtinen

NVIDIA
Aalto University

投稿日付(yyyy/MM/dd)

2017/10/27

概要

新規性・差分

手法

結果

コメント

icoxfog417 added CNN ComputerVision labels

Member Author

icoxfog417 commented Oct 28, 2017

なぜかTheano/Lasagne実装

https://github.com/tkarras/progressive_growing_of_gans

Member Author

icoxfog417 commented Nov 7, 2017

PyTorchの実装が公開
https://github.com/ptrblck/prog_gans_pytorch_inference

Member Author

icoxfog417 commented Feb 2, 2018

画像だけでなく音声にも適用できるよう実装したコード(PyTorch製)。

https://github.com/deepsound-project/pggan-pytorch

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment