Skip to content

A model compression and acceleration toolbox based on pytorch.

License

Notifications You must be signed in to change notification settings

haiduo/Sparsebit

 
 

Repository files navigation

Introduction

Sparsebit is a toolkit with pruning and quantization capabilities. It is designed to help researchers compress and accelerate neural network models by modifying only a few codes in existing pytorch project.

Quantization

Quantization turns full-precision params into low-bit precision params, which can compress and accelerate the model without changing its structure. This toolkit supports two common quantization paradigms, Post-Training-Quantization and Quantization-Aware-Training, with following features:

  • Benefiting from the support of torch.fx, Sparsebit operates on a QuantModel, and each operation becomes a QuantModule.
  • Sparsebit can easily be extended by users to accommodate their own researches. Users can register to extend important objects such as QuantModule, Quantizer and Observer by themselves.
  • Exporting QDQ-ONNX is supported, which can be loaded and deployed by backends such as TensorRT and OnnxRuntime.

Results

  • PTQ results on ImageNet-1k: link
  • PTQ results of Vision Transformer on ImageNet-1k: link
  • PTQ results of YOLO related works on COCO: link
  • QAT results on ImageNet-1k: link

Sparse

Sparse is often used in deep learning to refer to operations such as reducing network parameters or network computation. At present, Sparse supported by the toolbox has the following characteristics:

  • Supports two types of pruning: structured/unstructured;
  • Supports a variety of operation objects including: weights, activations, model-blocks, model-layers, etc.;
  • Supports multiple pruning algorithms: L1-norm/L0-norm/Fisher-pruning/Hrank/Slimming...
  • Users can extend a custom pruning algorithm easily by defining a Sparser
  • Using ONNX as the export format for the pruned model

Resources

Documentations

Detailed usage and development guidance is located in the document. Refer to: docs

CV-Master

  • We maintain a public course on quantification at Bilibili, introducing the basics of quantification and our latest work. Interested users can join the course.video
  • Aiming at better enabling users to understand and apply the knowledge related to model compression, we designed related homework based on Sparsebit. Interested users can complete it by themselves.quantization_homework

Plan to re-implement

Join Us

  • Welcome to be a member (or an intern) of our team if you are interested in Quantization, Pruning, Distillation, Self-Supervised Learning and Model Deployment.
  • Submit your resume to: [email protected]

Acknowledgement

Sparsebit was inspired by several open source projects. We are grateful for these excellent projects and list them as follows:

License

Sparsebit is released under the Apache 2.0 license.

About

A model compression and acceleration toolbox based on pytorch.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 91.3%
  • Cuda 7.8%
  • C++ 0.9%