Starred repositories
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA/Tensor Cores Kernels, HGEMM, FA-2 MMA.🎉
A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.
(2020-2022)The PyTorch version of SiamFC，SiamRPN，DaSiamRPN, UpdateNet , SiamDW, SiamRPN++, SiamMask, SiamFC++, SiamCAR, SiamBAN, Ocean, LightTrack , TrTr, NanoTrack; Visual object tracking based on…
This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!
A PyTorch-based model pruning toolkit for pre-trained language models
A PyTorch-based knowledge distillation toolkit for natural language processing
The official implementation for the paper [ODTrack: Online Dense Temporal Token Learning for Visual Tracking].
Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything
Visual tracking library based on PyTorch.
The framework of training large language models，support lora, full parameters fine tune etc, define yaml to start training/fine tune of your defined models, data and methods. Easy define and easy s…
CSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/SaaS solutions, with features comparable to Hugging Face. Gain…
ying-fu / LMOT
Forked from xinzwang/LMOTMulti-Object Tracking in the Dark (Accepted by CVPR 2024)
When clone from github.com, build mirror cache to improve clone speed
A RSS, Atom and JSON Feed generator for Node.js, making content syndication simple and intuitive! 🚀
Easy to maintain open source documentation websites.
This is a collection of our NAS and Vision Transformer work.
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo
[AAAI 2024] UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation. UCMCTrack achieves SOTA on MOT17 using estimated camera parameters.
Implementation for Object Permanence Emerges in a Random Walk along Memory
[ICCV 2023] ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks