PyTorch implementation of the Crafting Better Contrastive Views for Siamese Representation Learning

Last update: Dec 28, 2022

Related tags

Overview

Crafting Better Contrastive Views for Siamese Representation Learning

This is the official PyTorch implementation of the ContrastiveCrop paper:

@article{peng2022crafting,
  title={Crafting Better Contrastive Views for Siamese Representation Learning},
  author={Peng, Xiangyu and Wang, Kai and Zhu, Zheng and You, Yang},
  journal={arXiv preprint arXiv:2202.03278},
  year={2022}
}

This repo includes PyTorch implementation of SimCLR, MoCo, BYOL and SimSiam, as well as their DDP training code.

Preparation

Create a python enviroment with pytorch >= 1.8.1.
pip install -r requirements.txt
Modify dataset root in the config file.

Pre-train

# MoCo, CIFAR-10
python DDP_moco_ccrop.py configs/small/cifar10/moco_alpha0.1_th0.1.py

# SimSiam, CIFAR-100
python DDP_simsiam_ccrop.py configs/small/cifar100/simsiam_alpha0.1_th0.1.py

Linear Evaluation

# CIFAR-10
python DDP_linear.py configs/linear/cifar10_res18.py --load ./checkpoints/small/cifar10/moco_alpha0.1_th0.1/last.pth

# CIFAR-100
python DDP_linear.py configs/linear/cifar100_res18.py --load ./checkpoints/small/cifar100/simsiam_alpha0.1_th0.1/last.pth

More models and datasets coming soon.

PyTorch implementation of the Crafting Better Contrastive Views for Siamese Representation Learning

Related tags

Overview

Crafting Better Contrastive Views for Siamese Representation Learning

Preparation

Pre-train

Linear Evaluation

Owner

Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection

Automatic tool focused on deriving metallicities of open clusters

New AidForBlind - Various Libraries used like OpenCV and other mentioned in Requirements.txt

Efficient face emotion recognition in photos and videos

Optimizes image files by converting them to webp while also updating all references.

OoD Minimum Anomaly Score GAN - Code for the Paper 'OMASGAN: Out-of-Distribution Minimum Anomaly Score GAN for Sample Generation on the Boundary'

Boosting Adversarial Attacks with Enhanced Momentum (BMVC 2021)

A framework that constructs deep neural networks, autoencoders, logistic regressors, and linear networks

Leveraging OpenAI's Codex to solve cornerstone problems in Music

A simple log parser and summariser for IIS web server logs

Diffusion Probabilistic Models for 3D Point Cloud Generation (CVPR 2021)

Logistic Bandit experiments. Official code for the paper "Jointly Efficient and Optimal Algorithms for Logistic Bandits".

The reference baseline of final exam for XMU machine learning course

Controlling Hill Climb Racing with Hand Tacking

Half Instance Normalization Network for Image Restoration

Efficient Lottery Ticket Finding: Less Data is More

Anatomy of Matplotlib -- tutorial developed for the SciPy conference

(CVPR 2022) Pytorch implementation of "Self-supervised transformers for unsupervised object discovery using normalized cut"

Generating Fractals on Starknet with Cairo

Integrated physics-based and ligand-based modeling.