d-fine

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]

Inference and fine-tuning examples for vision models from 🤗 Transformers

Plug-and-Play Custom Parsers for AI Models in NVIDIA DeepStream SDK. Supported YOLOv11, D-FINE, SCRFD model.

Mono repo with sinapsis templates for object detection

TensorRT in Practice: Model Conversion, Extension, and Advanced Inference Optimization

D-FINEをGoogle Colaboratory上で訓練しONNXのファイルをエクスポートするサンプル

State-of-the-art object detection in 3 lines of Python — D-FINE and RF-DETR behind a unified Ultralytics-style API, Apache 2.0. Train, export to Core ML / ONNX / TensorRT, deploy to iPhone.

DEIMをGoogle Colaboratory上で訓練しONNXのファイルをエクスポートするサンプル

D-FINEのPythonでのONNX推論サンプル

DEIMのPythonでのONNX推論サンプル

Object detection is the computer vision task of detecting instances (such as humans, buildings, or cars) in an image. Object detection models receive an image as input and output coordinates of the bounding boxes and associated labels of the detected objects.

Open source Video Management System

D-FINEをカスタムデータセットで学習するプログラム

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.

Reproducible subject-disjoint benchmark of lightweight object detectors for real-time visible driver-cue localization in RGB and NIR imagery; planned for CAISAIS 2026.

Progetto di tesi sperimentale in Informatica: indagine sul disallineamento tra metriche di detection (mAP) e accuratezza clinica (endotipo, gradi AICNA) nel rilevamento automatico di citotipi nasali. Confronto tra YOLOv10, RF-DETR e D-FINE sul dataset NMCD.

This repository contains the code to run the D-FINE object detection model using ONNX Runtime in a Node.js environment. The script processes an input image, performs inference to detect objects, and saves the image with bounding boxes drawn around the detected objects