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

Patch Rotation: A Self-Supervised Auxiliary Task for Robustness and Accuracy of Supervised Models

git《Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser》(2021) GitHub: [fig5]

Elegy is a framework-agnostic Trainer interface for the Jax ecosystem.

Reinforcement learning framework and algorithms implemented in PyTorch.

AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition

Code and data form the paper BERT Got a Date: Introducing Transformers to Temporal Tagging

Research on controller area network Intrusion Detection Systems

CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator

The official implementation of You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient.

Codes for NAACL 2021 Paper "Unsupervised Multi-hop Question Answering by Question Generation"

SmoothGrad implementation in PyTorch

LoL Runes Recommender With Python

Source code for our paper "Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversations"

PyTorch code for our paper "Image Super-Resolution with Non-Local Sparse Attention" (CVPR2021).

Home for cuQuantum Python & NVIDIA cuQuantum SDK C++ samples

Fast, accurate and reliable software for algebraic CT reconstruction

Official code for the paper: Deep Graph Matching under Quadratic Constraint (CVPR 2021)

Official Implementation for Fast Training of Neural Lumigraph Representations using Meta Learning.

Official PyTorch implementation of PS-KD

Source Code for DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances (https://arxiv.org/pdf/2012.01775.pdf)