# ist-daslab/acdc

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/ist-daslab-acdc).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

23 stars · 4 forks · Python · Apache-2.0

## Links

- GitHub: https://github.com/IST-DASLab/ACDC
- awesome-repositories: https://awesome-repositories.com/repository/ist-daslab-acdc.md

## Description

This code allows replicating the image experiments of AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks. This code allows for training compressed and decompressed WideResNet models for CIFAR-100, ResNet50 and MobileNet models for Imagenet (also for 2:4 sparsity), and…

## Tags

### Part of an Awesome List

- [Weight Pruning](https://awesome-repositories.com/f/awesome-lists/ai/weight-pruning.md) — Alternating compressed and decompressed training for deep networks.