Detr Python Packages

rfdetr

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]

mmdet

OpenMMLab Detection Toolbox and Benchmark

easydetect

Real-time object detection you can ship — Easydetect with PyTorch training, OpenVINO inference, and a browser app. Apache-2.0.

rtdetr

Real-time object detection you can ship — RT-DETR with PyTorch training, OpenVINO inference, and a browser app. Apache-2.0.

paddledet

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

dfine-seg

D-FINE-seg Object Detection and Segmentation Framework (Train, Export, Inference)

autodistill-detr

DETR (resnet-50) module for use with Autodistill.

pydfine

Config-first, Ultralytics-style Python library for the D-FINE real-time object detector: predict, train, validate, and export (ONNX) detection & segmentation from one typed class. No YAML.

nitid

One library. DETR made simple.

rfdetr-ghost

Drop-in performance optimization layer for RF-DETR using custom fused CuteDSL & Triton kernels: same API, significantly faster execution.

avi-mmdet

OpenMMLab Detection Toolbox and Benchmark

mmdet-taeuk4958

OpenMMLab Detection Toolbox and Benchmark

torchxai-explain

Explainability and saliency maps for PyTorch vision models — GradCAM, EigenCAM, Attention Rollout for CNNs, Vision Transformers (ViT), CLIP, YOLO, DETR, DINO. One-line API.

mmdet-open

OpenMMLab Detection Toolbox and Benchmark

detection-fusion

DetectionFusion is a Python toolkit for fusing multiple object detection results with ground truth validation and error analysis. Perfect for scenarios where you have multiple object detection models - leverage the wisdom of crowds to improve detection quality through consensus-based ensemble learning, and evaluate performance with rigorous ground

psvis

OpenMMLab Detection Toolbox and Benchmark

py-sues

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

ppdet-notebook

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

rfdetr-isarsoft

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]

yolov7-d2

🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

ppdet

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

paddledetection-test

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.