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

Receptive Field Block Net for Accurate and Fast Object Detection, ECCV 2018

UnpNet - Rethinking 3-D LiDAR Point Cloud Segmentation(IEEE TNNLS)

Official implementation of EfficientPose

A super lightweight Lagrangian model for calculating millions of trajectories using ERA5 data

Rational Activation Functions - Replacing Padé Activation Units

Code and description for my BSc Project, September 2021

Awesome Graph Classification - A collection of important graph embedding, classification and representation learning papers with implementations.

A simple, high level, easy-to-use open source Computer Vision library for Python.

nextPARS, a novel Illumina-based implementation of in-vitro parallel probing of RNA structures.

Employs neural networks to classify images into four categories: ship, automobile, dog or frog

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

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.

Instant Real-Time Example-Based Style Transfer to Facial Videos

Efficient Training of Audio Transformers with Patchout

Pytorch Performace Tuning, WandB, AMP, Multi-GPU, TensorRT, Triton

Code and Data for NeurIPS2021 Paper "A Dataset for Answering Time-Sensitive Questions"

Code for the paper: "On the Bottleneck of Graph Neural Networks and Its Practical Implications"

A tensorflow implementation of GCN-LPA

Repository sharing code and the model for the paper "Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes"

Implementation of Invariant Point Attention, used for coordinate refinement in the structure module of Alphafold2, as a standalone Pytorch module