https://github.com/ducha-aiki/lsuv-keras
Simple implementation of the LSUV initialization in keras
https://github.com/ducha-aiki/lsuv-keras
convolutional-networks convolutional-neural-networks deeplearning initialization keras lsuv lsuv-initialization
Last synced: about 1 month ago
JSON representation
Simple implementation of the LSUV initialization in keras
- Host: GitHub
- URL: https://github.com/ducha-aiki/lsuv-keras
- Owner: ducha-aiki
- License: bsd-2-clause
- Created: 2016-08-28T08:29:14.000Z (almost 9 years ago)
- Default Branch: master
- Last Pushed: 2019-07-15T19:32:42.000Z (almost 6 years ago)
- Last Synced: 2025-03-30T14:51:10.512Z (2 months ago)
- Topics: convolutional-networks, convolutional-neural-networks, deeplearning, initialization, keras, lsuv, lsuv-initialization
- Language: Python
- Size: 9.77 KB
- Stars: 67
- Watchers: 7
- Forks: 22
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Layer-sequential unit-variance (LSUV) initialization for Keras
This is sample code for LSUV and initializations, implemented in python script within Keras framework.
Usage:
from lsuv_init import LSUVinit
...
batch_size = 32
model = LSUVinit(model, train_imgs[:batch_size,:,:,:])
LSUV initialization is described in:
Mishkin, D. and Matas, J.,(2015). All you need is a good init. ICLR 2016 [arXiv:1511.06422](http://arxiv.org/abs/1511.06422).
Original Caffe implementation [https://github.com/ducha-aiki/LSUVinit](https://github.com/ducha-aiki/LSUVinit)
Torch re-implementation [https://github.com/yobibyte/torch-lsuv](https://github.com/yobibyte/torch-lsuv)
PyTorch implementation [https://github.com/ducha-aiki/LSUV-pytorch](https://github.com/ducha-aiki/LSUV-pytorch)
**New!** Thinc re-implementation [LSUV-thinc](https://github.com/explosion/thinc/blob/e653dd3dfe91f8572e2001c8943dbd9b9401768b/thinc/neural/_lsuv.py)