Skip to content

rakib1521/SimCLR-A-Simple-Framework-for-Contrastive-Learning-of-Visual-Representations

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 

Repository files navigation

SimCLR

A PyTorch Google Colab implementation of SimCLR based on ICML 2020 paper A Simple Framework for Contrastive Learning of Visual Representations.

Requirements

  • timm
  • kaggle
  • opencv-python-headless==4.1.2.30
  • wandb

Dataset

This code is implemented using Google Colab Free GPU and "Apparel images dataset" is used in this implementation.

Results

There are some difference between this implementation and official implementation, the model ('ResNet18','efficientnet_b0') is trained on one COLAB GPU:

Wandb log

Authored by:

Rakib Hossain Rifat

Machine Learning Engineer

Polyfins Technology Inc.

About

PyTorch Google Colab implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published