Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.

PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.

Ultralytics YOLO tutorials for Colab, Kaggle, and SageMaker covering training, inference, export, and vision tasks.

Python SDK for Ultralytics HUB: authenticate and programmatically create, manage, upload, export, and deploy computer vision models, datasets, and projects.

A library for exporting Spark ML models and pipelines to PFA

Ultralytics YOLO26 quickstart for detection, instance and semantic segmentation, classification, pose, OBB, and tracking.

Any PyTorch model to NNEF exchange format

TouchDesigner geometry utils

Ultralytics YOLOv8 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

YOLOv12 Underwater Object Detection is an open-source suite for underwater object detection, built on YOLOv12. It offers an end-to-end pipeline with GPU-accelerated training, customizable data augmentations, real-time inference via Gradio, and support for model export (ONNX & PyTorch).

Ultralytics YOLO11 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

Blender add-on to import/export BattleForge / Skylords Reborn 3D models, animations, materials, and collisions (.drs, .bmg, .ska).

HGM Viewer is a 3D model viewer and exporter for Haemimont Games model format .hgm used in the Sol Engine (Jagged Alliance 3 etc.)

crossdata graphics tests

Convert XGBoost models (XGBRegressor/XGBClassifier) to Excel formula expressions for spreadsheet deployment

Modular pipeline for building RAG and LLM workflows in Colab, including tokenizer/chunk/embed notebooks and CoreML model exporters for iOS. Part of the NoesisNoema project.

A standalone version of the next PyTorch ONNX exporter

A powerful GUI tool to manage YOLO training runs, run batch profile-based model exports (ONNX, TensorRT, OpenVINO) with custom precision/opset configurations, execute automated post-export scripting pipelines, and preview test model inference in real-time.

Experimental system model generator for RTS

Machine Learning model optimizer and exporter for embedded systems and mobile platforms