Giter Site home page Giter Site logo

soft-nms's Introduction

Soft-NMS

Implements of Soft NMS algorithm

Original Paper:Improving Object Detection With One Line of Code

Description

This repo include :

  1. Python version of Soft NMS algorithm
  2. Pytorch version of Soft NMS algorithm

Speed analysis

The average running time was obtained using 1000 tests, and 100 candidate boxes and scores were randomly generated for each test. Because the algorithm has many complex operations that are not suitable for GPU processing, the GPU version of the algorithm is rather slow.

version run time(ms) device
python cpu version 21.472 i9-7900X [email protected]
pytorch cpu version 21.778 i9-7900X [email protected]
pytorch gpu version 60.128 TITAN Xp

ToDo

  • PyTorch CUDA version
  • speed analysis
  • Keras version

soft-nms's People

Contributors

docf avatar

Watchers

James Cloos avatar paper2code - bot avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.