Skip to content
master
Switch branches/tags
Go to file
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 

README.md

PENNI

This repo provides the code of PENNI: Pruned Kernel Sharing for Efficient CNN Inference.

Install Requirement Packages:

pip install -r requirements.txt

If you find this work is helpful, cite with:

@inproceedings{li2020penni,
title={PENNI: Pruned Kernel Sharing for Efficient CNN Inference},
author={Li, Shiyu and Hanson, Edward and Li, Hai and Chen, Yiran},
booktitle={International Conference on Machine Learning},
year={2020}
}

Acknowledgement

The resnet-56 implementation is from: pytorch_resnet_cifar10

We count the FLOPs number with the modified version of pytorch-OpCounter

The ImageNet training script is derived from apex

About

PENNI: Pruned Kernel Sharing for Efficient CNN Inference

Resources

License

Releases

No releases published

Packages

No packages published