https://github.com/zib-iol/compression-aware-sfw
Code to reproduce the experiments of "Compression-aware Training of Neural Networks using Frank-Wolfe"
https://github.com/zib-iol/compression-aware-sfw
compression constrained-optimization deep-learning machine-learning neural-network pruning pytorch
Last synced: about 2 months ago
JSON representation
Code to reproduce the experiments of "Compression-aware Training of Neural Networks using Frank-Wolfe"
- Host: GitHub
- URL: https://github.com/zib-iol/compression-aware-sfw
- Owner: ZIB-IOL
- Created: 2022-05-23T10:37:25.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2023-02-22T09:22:36.000Z (about 2 years ago)
- Last Synced: 2025-02-07T01:32:09.088Z (3 months ago)
- Topics: compression, constrained-optimization, deep-learning, machine-learning, neural-network, pruning, pytorch
- Language: Python
- Homepage:
- Size: 47.9 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Citation: citation.bib
Awesome Lists containing this project
README
## Compression-aware Training of Neural Networks using Frank-Wolfe
*Authors: [Max Zimmer](https://maxzimmer.org/), [Christoph Spiegel](http://www.christophspiegel.berlin/), [Sebastian Pokutta](http://www.pokutta.com/)*
This repository contains the code to reproduce the experiments from the ["Compression-aware Training of Neural Networks using Frank-Wolfe" (arXiv:2205.11921)](https://arxiv.org/abs/2205.11921) paper.
The code is based on [PyTorch 1.9](https://pytorch.org/) and the experiment-tracking platform [Weights & Biases](https://wandb.ai).
### Structure and Usage
Experiments are started from the following file:
- [`main.py`](main.py): Starts experiments using the dictionary format of Weights & Biases.
The rest of the project is structured as follows:
- [`strategies`](strategies): Contains all used sparsification methods.
- [`runners`](runners): Contains classes to control the training and collection of metrics.
- [`metrics`](metrics): Contains all metrics as well as FLOP computation methods.
- [`models`](models): Contains all model architectures used.
- [`optimizers`](optimizers): Contains reimplementations of SFW, SGD and Proximal SGD.
### Citation
In case you find the paper or the implementation useful for your own research, please consider citing:
```
@Article{zimmer2022,
author = {Max Zimmer and Christoph Spiegel and Sebastian Pokutta},
title = {Compression-aware Training of Neural Networks using Frank-Wolfe},
year = {2022},
archiveprefix = {arXiv},
eprint = {2205.11921},
primaryclass = {cs.LG},
}
```