jie311

TinySAM

Official PyTorch implementation of "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"

ADAS_Detection

BDD100K dataset, detection, ADAS, YOLO detection, label

BCEmbedding

Netease Youdao's open-source embedding and reranker models for RAG products.

cleanlab

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

cooperative-foundational-models

Official code for our paper "Enhancing Novel Object Detection via Cooperative Foundational Models"

DB-GPT

AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents

DETR_onnx_tensorRT

DETR tensorRT 部署。

DETR_onnx_tensorRT_V2

DETR tensor去除推理过程无用辅助头+fp16部署再次加速+解决转tensorrt 输出全为0问题的新方法。

Dipoorlet

Offline Quantization Tools for Deploy.

dpr

[WACV2024] Patch-based Selection and Refinement for Early Object Detection

edgeai-yolox

YOLOX-ti-lite models are optimized for deployment on TI edge processors

FOMO

Official Pytorch code for Open World Object Detection in the Era of Foundation Models

HKD_for_person_search

InfoBatch

Lossless Training Speed Up by Unbiased Dynamic Data Pruning

multas

Multi-Task Self-training for Object detection and Semantic segmentation

MultiAugs

Code for my paper "Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency Training"

onnx_quant_tool

An onnx-based quantitation tool.

QAnything

Question and Answer based on Anything.

RT-DETR-official

Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

SlimSAM

SlimSAM: 0.1% Data Makes Segment Anything Slim

TBPS-CLIP

【AAAI 2024】An Empirical Study of CLIP for Text-based Person Search

UCMCTrack

[AAAI 2024] UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation. UCMCTrack ranks first on MOT17 without using any appearance cues.

UCMCTrack-cpp

A C++ implementation for UCMCTrack (SOTA in MOT17)

Uni-YOLO

A universal object detector for robots that has the ability to detect any object in the open world.

vfe.pytorch

Video Feature Enhancement with PyTorch

WidthFormer

WidthFormer: Toward Efficient Transformer-based BEV View Transformation

YOLO-Pruning-RKNN

Easy Training Official YOLOv8、YOLOv7、YOLOv6、YOLOv5 and Prune all_model using Torch-Pruning!

YOLO-World

Real-Time Open-Vocabulary Object Detection

YOLOPoint

Joint Keypoint and Object Detection

zsd_yolo_v7