Giter VIP home page Giter VIP logo

moco_v2's Introduction

MoCo v2 Implementation with Pytorch

  • Unofficial implementation of the paper Improved Baselines with Momentum Contrastive Learning

0. Develop Environment

  • Check env.txt for more details

1. Implementation Details

  • data.py : data augmentations, dataset
  • main_linear.py : only train linear classifier with frozen backbone
  • main_pretrain.py : pre-train backbone
  • models_linear.py : model for linear probing
  • models_moco.py : model for pre-train
  • utils.py : utils such as scheduler, logger
  • logs : log files
  • visualize : visualize pretrain, linear probing log (acc, lr, train loss, val loss)

2. Linear Probing Result Comparison on ImageNet

Source Score Detail
Paper 67.7 200 epochs
Paper 71.1 800 epochs
Current Repo 67.41 200 epochs, query
Current Repo 67.50 200 epochs, key
Current Repo 70.12 800 epochs, query
Current Repo 70.15 800 epochs, key

3. Reference

moco_v2's People

Contributors

jasonlee1995 avatar

Watchers

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.