← 开源
HobbitLong

PyContrast

PyTorch implementation of Contrastive Learning methods

Model DevelopmentTraining toolkitsPython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
1.99k
Star
180
Fork
+0
本周
8
贡献者
创建于 2020-05-21 · 更新于 2026-09-19 · 今日第 7577 名
主要开发者
README

PyContrast

This repo lists recent contrastive learning papers, and includes code for many of them.

Paper List

Find awesome contrastive learning paper.

PyTorch Code

For the reference implementation of SoTA methods, (e.g., InstDis, CMC, MoCo, ...), see pycontrast.

Pre-trained Models

A set of ImageNet unsupervised pre-training models are provided. Find them in model zoo.

Object Detection

Unsupervised pre-training models outperform supervised pre-training models on PASCAL VOC and COCO. Find in detection.