Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/hlld/cross-iteration-bn
a tensorflow-1.x implementation of Cross-Iteration BatchNormalization
https://github.com/hlld/cross-iteration-bn
Last synced: about 1 month ago
JSON representation
a tensorflow-1.x implementation of Cross-Iteration BatchNormalization
- Host: GitHub
- URL: https://github.com/hlld/cross-iteration-bn
- Owner: hlld
- License: apache-2.0
- Created: 2020-07-06T09:47:35.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2021-01-29T02:32:11.000Z (almost 4 years ago)
- Last Synced: 2024-05-18T22:33:39.790Z (7 months ago)
- Language: Python
- Size: 24.4 KB
- Stars: 2
- Watchers: 2
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-normalization-techniques - [Python Reference
README
## Cross-Iteration BatchNormalization
this repository contains the tensorflow-1.x implementation of the recent Cross-Iteration BatchNormalization method. Please visit [Cross-iterationBatchNorm]( https://github.com/Howal/Cross-iterationBatchNorm) if you're interested about the original PyTorch Version. Or you can read [arxiv](https://arxiv.org/abs/2002.05712) for more details.
## Problem Recording
I was wondering that why this implementation always has a lower performance compared to the original BN. Is it because the dataset I use is too small or what I did wrong? If you know this please please tell me.
## About The Author
A boring master student from CQUPT. email: [email protected]