Coder Social home page Coder Social logo

ducha-aiki / lsuv-pytorch Goto Github PK

View Code? Open in Web Editor NEW
58.0 5.0 8.0 9.13 MB

Simple implementation of the LSUV initialization in PyTorch

License: BSD 2-Clause "Simplified" License

Python 100.00%
pytorch lsuv lsuv-initialization convolutional-neural-networks convolutional-networks deeplearning initialization cnn

lsuv-pytorch's Introduction

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

NEW repo: 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

LSUV initialization is described in:

Mishkin, D. and Matas, J.,(2015). All you need is a good init. ICLR 2016 arXiv:1511.06422.

Original Caffe implementation https://github.com/ducha-aiki/LSUVinit

Torch re-implementation https://github.com/yobibyte/torch-lsuv

Keras implementation: https://github.com/ducha-aiki/LSUV-keras

New! Thinc re-implementation LSUV-thinc

lsuv-pytorch's People

Contributors

ducha-aiki avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

lsuv-pytorch's Issues

Runtime error

How can I use LSUV instead of Xavier in my NN, please let me know if I can implement it like this or is there any other way:
LSUVinit(model, m.weight)
Can i use weights as my data or it will take images or any other form of data
ERROR
RuntimeError: Given groups=1, weight of size [64, 3, 3, 3], expected input[16, 64, 1, 1] to have 3 channels, but got 64 channels instead

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.