https://github.com/ducha-aiki/lsuv-pytorch

Simple implementation of the LSUV initialization in PyTorch
https://github.com/ducha-aiki/lsuv-pytorch

cnn convolutional-networks convolutional-neural-networks deeplearning initialization lsuv lsuv-initialization pytorch

Last synced: 8 days ago
JSON representation

Simple implementation of the LSUV initialization in PyTorch

• Host: GitHub
• URL: https://github.com/ducha-aiki/lsuv-pytorch
• Owner: ducha-aiki
• License: bsd-2-clause
• Created: 2017-07-19T12:38:55.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2024-01-16T11:56:24.000Z (10 months ago)
• Last Synced: 2024-11-02T02:33:04.324Z (15 days ago)
• Topics: cnn, convolutional-networks, convolutional-neural-networks, deeplearning, initialization, lsuv, lsuv-initialization, pytorch
• Language: Python
• Size: 8.92 MB
• Stars: 58
• Watchers: 5
• Forks: 8
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Layer-sequential unit-variance (LSUV) initialization for PyTorch

# NEW repo: [ducha-aiki/lsuv](https://github.com/ducha-aiki/lsuv)

```

pip install lsuv

```

This is sample code for LSUV and initializations, implemented in python script within PyTorch framework. 

Usage:

    from LSUV import LSUVinit

    ...

    model = LSUVinit(model,data)

See detailed example in [example.py](example.py)

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)

Keras implementation: [https://github.com/ducha-aiki/LSUV-keras](https://github.com/ducha-aiki/LSUV-keras)

**New!** Thinc re-implementation [LSUV-thinc](https://github.com/explosion/thinc/blob/e653dd3dfe91f8572e2001c8943dbd9b9401768b/thinc/neural/_lsuv.py)