Skip to content
Learning both Weights and Connections for Efficient Neural Networks https://arxiv.org/abs/1506.02626
Jupyter Notebook Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
models Testing WideResNet Aug 13, 2019
resources Crop Jun 27, 2019
.gitignore Use masks during training so that they get saved into the state_dict Jun 24, 2019
Plots.ipynb ResNet exps Jun 27, 2019
README.md Update README.md Jun 27, 2019
prune.py ResNet exps Jun 27, 2019
train.py Testing WideResNet Aug 13, 2019
utils.py ResNet exps Jun 27, 2019

README.md

Learning both Weights and Connections for Efficient Neural Networks

A PyTorch implementation of this paper.

I'm currently in the process of updating this to work with the latest version of PyTorch! Currently the only network type that works is ResNet - other networks coming soon.

To run, try:

python train.py --model='resnet34' --checkpoint='resnet34'
python prune.py --model='resnet34' --checkpoint='resnet34'

Summary

Given a family of ResNets, we can construct a Pareto frontier of the tradeoff between accuracy and number of parameters:

alt text

Han et al. posit that we can beat this Pareto frontier by leaving network structures fixed, but removing individual parameters:

alt text

You can’t perform that action at this time.