wangguanan

light-reid

[ECCV2020] a toolbox of light-reid learning for faster inference, speed both feature extraction and retrieval stages up to >30x

HOReID

[CVPR2020] High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification

JSIA-ReID

[AAAI2020] Cross-Modality Paired-Images Generation for RGB-InfraredPerson Re-Identification

AlignGAN

[ICCV2019] RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment

Pytorch-Person-ReID-Baseline-PCB-Beyond-Part-Models

A strong implementation of PCB (Beyond Part Models), outperforming all existing implementations.

mengone

This is a tutorial for deep learning libraru

wangguanan.github.io

fast-reid

SOTA ReID Methods and Toolbox

wangguanan

CVPR2020-Code

CVPR 2020 论文开源项目合集

pytorch-center-loss

Pytorch implementation of Center Loss

awesome-tips

Bias-Eliminate-DA-ReID

Our solution to Domain Adaptive Pedestrian Re-identification in VisDA2020

DALLE-pytorch

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

deep-person-reid

Torchreid: Deep learning person re-identification in PyTorch.

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.

gpt-3

GPT-3: Language Models are Few-Shot Learners

HAA

MegEngine

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

MiniGPT-4

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

mmsegmentation

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

MOSS

An open-source tool-augmented conversational language model from Fudan University

NGCF-PyTorch

PyTorch Implementation for Neural Graph Collaborative Filtering

ShuffleNet-Series

sort

Simple, online, and realtime tracking of multiple objects in a video sequence.

Swin-Transformer-Object-Detection

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

vision_transformer

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

weak-to-strong

wenda

闻达：一个LLM调用平台。为小模型外挂知识库查找和设计自动执行动作，实现不亚于于大模型的生成能力