rtdetr 开源项目推荐（31 个）

lyuwenyu /RT-DETR

[CVPR 2024] 官方 RT-DETR（RTDETR paddle pytorch），实时检测 Transformer，DETR 在实时目标检测上击败 YOLO。

marcoslucianops /DeepStream-Yolo

NVIDIA DeepStream SDK 8.0 / 7.1 / 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models

Koldim2001 /YOLO-Patch-Based-Inference

用于YOLO小对象检测和实例分割的Python库

YOLOSHOW /YOLOSHOW

YOLO Show -YOLOv 11/YOLOv 10/YOLOv 9/YOLOv 8/YOLOv 7/YOLOv 5/ RTDETR / Sam /ALEALESAM/ FastSAM/YOLOv 11/YOLOv 10基于Pyside 6的YOLO图形用户界面

bharath5673 /Deepstream

deepstream 上的 yolov3、yolo12、dino、分割、人脸、姿态、关键点

Li-Hongda /TensorRT_Inference_Demo

A repo that uses TensorRT to deploy wll-trained models.Support RTDETR,YOLO-NAS,YOLOV5,YOLOV6,YOLOV7,YOLOV8,YOLOX.

zz990099 /EasyDeploy

C++ implementations of YOLOv8/YOLO26, RT-DETR-V2(RTDETR), MobileSAM, and NanoSAM on TensorRT, ONNX Runtime, and RKNN.

int11 /RTDETR-PyTorch

RT-DETR for pytorch

MMUZAMMUL /GOIS

Enhancing Tiny Object Detection Using Guided Object Inference Slicing (GOIS): An Efficient Dynamic Adaptive Framework for Fine-Tuned and Non-Fine-Tuned Deep Learning Models

yyq19990828 /DETR-series

RT-DETRv3、D-FINE、DEIM、RT-DETRv4 和 DEIMv2 的统一 PyTorch 实现——30 个 COCO 变体，一个 CLI 完成训练/评估/推理/导出。DETR 系列实时目标检测模型统一 PyTorch 实现

higher-hai /DCEA

A method to optimize the current SAR ship detection pipeline using the DEtection TRansformer (DETR) model.

Shazy021 /yolo-vs-rtdetr-benchmark

YOLOv8 vs RT-DETR: PyTorch/ONNX/TensorRT benchmarks on RTX 5080

ChungKein4320 /pcb-defect-detection-benchmark

Source-wise PCB defect detection benchmark with YOLOv11s, RT-DETR, Faster R-CNN, and a cleaned 6-class merged dataset.

clip5 /TensorRT-DETR

TensorRT-DETR 是面向 NVIDIA GPU 的 C++/CUDA/TensorRT 推理部署库。它提供用于检测、实例分割和姿态估计的 C++ 与 Python API。

dkozlov /fathomnet-2026-3rd-place

3rd-place private leaderboard solution for Kaggle FathomNet 2026, including source code, model checkpoints, final submissions, reproducibility notes, and writeup

SyedMIrtazaHyder /LiDAR_based_Object_Detection_and_Tracking

Final Year Project repository, where we developed a robust detection and tracking system using LiDAR data to run on the Jetson Xavier.

mevlt01001 /LADA-Detection

This repository enables training Ultralytics object detection models with the anchor-free LADA assignment algorithm and DFL-based regression. Multi-model feature fusion, joint training, and hybrid inference are also supported.

Def-Hashy /HashyCV

Modular computer vision framework powering detection, tracking, segmentation, and surveillance AI systems.

hpmezam /tesis_somnolencia

Detector de somnolencia - Ultralytics RTDETR

kongbai0123 /vision-workbench

Local-first Windows vision workbench: camera capture, annotation, dataset review and splits, versioned training, evaluation, and tqdm-based ETA.