# Ultralytics Docs

> Essential guides for YOLO11, YOLO26, and the Ultralytics library — setup, tutorials, and API reference.

## Home
- [Home](https://docs.ultralytics.com/): Discover Ultralytics YOLO - the latest in real-time object detection and image segmentation. Learn about its features and maximize its potential in your projects.
- [Quickstart](https://docs.ultralytics.com/quickstart): Learn how to install Ultralytics using pip, conda, or Docker. Follow our step-by-step guide for a seamless setup of Ultralytics YOLO.
- [CLI](https://docs.ultralytics.com/usage/cli): Explore the YOLO command line interface (CLI) for easy execution of detection tasks without needing a Python environment.
- [Python](https://docs.ultralytics.com/usage/python): Learn to integrate Ultralytics YOLO in Python for object detection, segmentation, semantic segmentation, and classification. Load and train models, and make predictions easily with our comprehensive guide.
- [Callbacks](https://docs.ultralytics.com/usage/callbacks): Explore Ultralytics callbacks for training, validation, exporting, and prediction. Learn how to use and customize them for your ML models.
- [Configuration](https://docs.ultralytics.com/usage/cfg): Optimize your Ultralytics YOLO model's performance with the right settings and hyperparameters. Learn about training, validation, and prediction configurations.
- [Simple Utilities](https://docs.ultralytics.com/usage/simple-utilities): Explore essential utilities in the Ultralytics package to speed up and enhance your workflows. Learn about data processing, annotations, conversions, and more.
- [Advanced Customization](https://docs.ultralytics.com/usage/engine): Learn to customize the Ultralytics YOLO Trainer for specific tasks. Step-by-step instructions with Python examples for maximum model performance.
- [YOLO26 🚀](https://docs.ultralytics.com/models/yolo26): YOLO26 from Ultralytics delivers unified, real-time, end-to-end vision models optimized for accurate and efficient deployment.

## Modes
- [Modes](https://docs.ultralytics.com/modes): Discover the diverse modes of Ultralytics YOLO26, including training, validation, prediction, export, tracking, and benchmarking. Maximize model performance and efficiency.
- [Train](https://docs.ultralytics.com/modes/train): Learn how to efficiently train object detection models using YOLO26 with comprehensive instructions on settings, augmentation, and hardware utilization.
- [Val](https://docs.ultralytics.com/modes/val): Learn how to validate your YOLO26 model with precise metrics, easy-to-use tools, and custom settings for optimal performance.
- [Predict](https://docs.ultralytics.com/modes/predict): Harness the power of Ultralytics YOLO26 for real-time, high-speed inference on various data sources. Learn about predict mode, key features, and practical applications.
- [Export](https://docs.ultralytics.com/modes/export): Learn how to export your YOLO26 model to various formats like ONNX, TensorRT, and CoreML. Achieve maximum compatibility and performance.
- [Track](https://docs.ultralytics.com/modes/track): Discover efficient, flexible, and customizable multi-object tracking with Ultralytics YOLO. Learn to track real-time video streams with ease.
- [Benchmark](https://docs.ultralytics.com/modes/benchmark): Learn how to evaluate your YOLO26 model's performance in real-world scenarios using benchmark mode. Optimize speed, accuracy, and resource allocation across export formats.

## Tasks
- [Tasks](https://docs.ultralytics.com/tasks): Explore Ultralytics YOLO26 for detection, segmentation, semantic segmentation, classification, OBB, and pose estimation with high accuracy and speed. Learn how to apply each task.
- [Detect](https://docs.ultralytics.com/tasks/detect): Learn about object detection with YOLO26. Explore pretrained models, training, validation, prediction, and export details for efficient object recognition.
- [Segment](https://docs.ultralytics.com/tasks/segment): Master instance segmentation using YOLO26. Learn how to detect, segment and outline objects in images with detailed guides and examples.
- [Semantic](https://docs.ultralytics.com/tasks/semantic): Learn about semantic segmentation using YOLO26. Assign class labels to every pixel for dense scene understanding with Cityscapes and ADE20K support.
- [Classify](https://docs.ultralytics.com/tasks/classify): Master image classification using YOLO26. Learn to train, validate, predict, and export models efficiently.
- [Pose](https://docs.ultralytics.com/tasks/pose): Discover how to use YOLO26 for pose estimation tasks. Learn about model training, validation, prediction, and exporting in various formats.
- [OBB](https://docs.ultralytics.com/tasks/obb): Discover how to detect objects with rotation for higher precision using YOLO26 OBB models. Learn, train, validate, and export OBB models effortlessly.

## Models
- [Models](https://docs.ultralytics.com/models): Discover a variety of models supported by Ultralytics, including YOLOv3 to YOLO26, NAS, SAM, and RT-DETR for detection, segmentation, semantic segmentation, and more.
- [YOLOv3](https://docs.ultralytics.com/models/yolov3): Discover YOLOv3 and its variants YOLOv3-Ultralytics and YOLOv3u. Learn about their features, implementations, and support for object detection tasks.
- [YOLOv4](https://docs.ultralytics.com/models/yolov4): Explore YOLOv4, a state-of-the-art real-time object detection model by Alexey Bochkovskiy. Discover its architecture, features, and performance.
- [YOLOv5](https://docs.ultralytics.com/models/yolov5): Explore YOLOv5u, an advanced object detection model with optimized accuracy-speed tradeoff, featuring anchor-free Ultralytics head and various pretrained models.
- [YOLOv6](https://docs.ultralytics.com/models/yolov6): Explore Meituan YOLOv6, a top-tier object detector balancing speed and accuracy. Learn about its unique features and performance metrics on Ultralytics Docs.
- [YOLOv7](https://docs.ultralytics.com/models/yolov7): Discover YOLOv7, the breakthrough real-time object detector with top speed and accuracy. Learn about key features, usage, and performance metrics.
- [YOLOv8](https://docs.ultralytics.com/models/yolov8): Discover Ultralytics YOLOv8, an advancement in real-time object detection, optimizing performance with an array of pretrained models for diverse tasks.
- [YOLOv9](https://docs.ultralytics.com/models/yolov9): Explore YOLOv9, a leap in real-time object detection, featuring innovations like PGI and GELAN, and achieving new benchmarks in efficiency and accuracy.
- [YOLOv10](https://docs.ultralytics.com/models/yolov10): Discover YOLOv10 for real-time object detection, eliminating NMS and boosting efficiency. Achieve top performance with a low computational cost.
- [YOLO11](https://docs.ultralytics.com/models/yolo11): Discover YOLO11, an advancement in real-time object detection, offering excellent accuracy and efficiency for diverse computer vision tasks.
- [YOLO12](https://docs.ultralytics.com/models/yolo12): Discover YOLO12, featuring groundbreaking attention-centric architecture for state-of-the-art object detection with unmatched accuracy and efficiency.
- [SAM (Segment Anything Model)](https://docs.ultralytics.com/models/sam): Explore the revolutionary Segment Anything Model (SAM) for promptable image segmentation with zero-shot performance. Discover key features, datasets, and usage tips.
- [SAM 2 (Segment Anything Model 2)](https://docs.ultralytics.com/models/sam-2): Discover SAM 2, the next generation of Meta's Segment Anything Model, supporting real-time promptable segmentation in both images and videos with state-of-the-art performance. Learn about its key features, datasets, and how to use it.
- [SAM 3 (Segment Anything Model 3)](https://docs.ultralytics.com/models/sam-3): Discover SAM 3, Meta's next evolution of the Segment Anything Model, introducing Promptable Concept Segmentation with text and image exemplar prompts for detecting all instances of visual concepts across images and videos.
- [MobileSAM (Mobile Segment Anything Model)](https://docs.ultralytics.com/models/mobile-sam): Discover MobileSAM, a lightweight and fast image segmentation model for mobile and edge applications. Compare its performance with SAM and YOLO models.
- [FastSAM (Fast Segment Anything Model)](https://docs.ultralytics.com/models/fast-sam): Discover FastSAM, a real-time CNN-based solution for segmenting any object in an image. Efficient, competitive, and ideal for various vision tasks.
- [YOLO-NAS (Neural Architecture Search)](https://docs.ultralytics.com/models/yolo-nas): Discover YOLO-NAS by Deci AI - a state-of-the-art object detection model with quantization support. Explore features, pretrained models, and implementation examples.
- [RT-DETR (Realtime Detection Transformer)](https://docs.ultralytics.com/models/rtdetr): Explore Baidu's RT-DETR, a Vision Transformer-based real-time object detector offering high accuracy and adaptable inference speed. Learn more with Ultralytics.
- [YOLO-World](https://docs.ultralytics.com/models/yolo-world): Explore the YOLO-World Model for efficient, real-time open-vocabulary object detection using Ultralytics YOLOv8 advancements. Achieve top performance with minimal computation.
- [YOLOE (Real-Time Seeing Anything)](https://docs.ultralytics.com/models/yoloe): YOLOE is a real-time open-vocabulary detection and segmentation model that extends YOLO with text, image, or internal vocabulary prompts, enabling detection of any object class with state-of-the-art zero-shot performance.

## Compare
- [Compare](https://docs.ultralytics.com/compare): Explore comprehensive comparisons of Ultralytics YOLO26, YOLO11, YOLOv10, RT-DETR, and other top object detection models. Use our benchmarks, charts, and decision guides to select the perfect model.
- [YOLO26 vs YOLO11](https://docs.ultralytics.com/compare/yolo26-vs-yolo11): Compare Ultralytics YOLO26 and YOLO11 performance, architecture, CPU inference, NMS-free design, and best-use cases to pick the right model for edge and production.
- [YOLO26 vs YOLOv10](https://docs.ultralytics.com/compare/yolo26-vs-yolov10): Technical comparison of Ultralytics YOLO26 and YOLOv10 — NMS-free end-to-end detection, CPU/edge speed, accuracy, architecture, and deployment tips.
- [YOLO26 vs YOLOv9](https://docs.ultralytics.com/compare/yolo26-vs-yolov9): Compare YOLO26 vs YOLOv9 NMS-free YOLO26, MuSGD optimizer, ProgLoss/STAL, CPU & edge performance, accuracy benchmarks and deployment tips.
- [YOLO26 vs YOLOv8](https://docs.ultralytics.com/compare/yolo26-vs-yolov8): Compare YOLO26 vs YOLOv8 architecture, benchmarks (mAP, latency), training innovations, and deployment tips for edge, mobile, and cloud vision applications.
- [YOLO26 vs YOLOv7](https://docs.ultralytics.com/compare/yolo26-vs-yolov7): Compare YOLO26 vs YOLOv7 NMS-free YOLO26, CPU-optimized performance, mAP & latency benchmarks, architecture differences, and deployment guidance for edge vs GPU.
- [YOLO26 vs YOLOv6](https://docs.ultralytics.com/compare/yolo26-vs-yolov6): Compare Ultralytics YOLO26 vs YOLOv6-3.0 — architecture, NMS-free CPU speedups, mAP benchmarks, and deployment guidance for edge, mobile, and robotics.
- [YOLO26 vs YOLOv5](https://docs.ultralytics.com/compare/yolo26-vs-yolov5): Compare YOLO26 vs YOLOv5 architectures, benchmarks, NMS-free inference, MuSGD optimizer, and recommended use cases for edge, robotics, and legacy systems.
- [YOLO26 vs RT-DETR](https://docs.ultralytics.com/compare/yolo26-vs-rtdetr): Compare Ultralytics YOLO26 and RTDETRv2 — architecture, mAP, CPU/GPU speed, benchmarks and deployment guidance to choose the right 2026 object detector.
- [YOLO26 vs PP-YOLOE+](https://docs.ultralytics.com/compare/yolo26-vs-pp-yoloe): Detailed comparison of Ultralytics YOLO26 vs PP-YOLOE+ benchmarks, architecture, CPU/GPU inference, and deployment guidance to pick the optimal object detection model.
- [YOLO26 vs DAMO-YOLO](https://docs.ultralytics.com/compare/yolo26-vs-damo-yolo): Compare Ultralytics YOLO26 and DAMO-YOLO architecture, accuracy, inference speed, and edge deployment (NMS-free, MuSGD, ONNX). Choose the best real-time object detector.
- [YOLO26 vs YOLOX](https://docs.ultralytics.com/compare/yolo26-vs-yolox): Compare Ultralytics YOLO26 and YOLOX benchmarks, NMS-free architecture, MuSGD optimizer, CPU/TensorRT speeds, and edge deployment for real-time object detection.
- [YOLO26 vs EfficientDet](https://docs.ultralytics.com/compare/yolo26-vs-efficientdet): Compare Ultralytics YOLO26 vs EfficientDet architecture, mAP & latency benchmarks, NMS-free design, and best deployment use cases for edge and cloud.
- [YOLO11 vs YOLO26](https://docs.ultralytics.com/compare/yolo11-vs-yolo26): Technical comparison of Ultralytics YOLO11 and YOLO26 - NMS-free, CPU-optimized YOLO26 with MuSGD. Speed, mAP, and deployment guidance for edge, cloud, and robotics.
- [YOLO11 vs YOLOv10](https://docs.ultralytics.com/compare/yolo11-vs-yolov10): Detailed technical comparison of YOLO11 and YOLOv10 for real-time object detection, covering performance, architecture, and ideal use cases.
- [YOLO11 vs YOLOv9](https://docs.ultralytics.com/compare/yolo11-vs-yolov9): Compare YOLO11 and YOLOv9 in architecture, performance, and use cases. Learn which model suits your object detection and computer vision needs.
- [YOLO11 vs YOLOv8](https://docs.ultralytics.com/compare/yolo11-vs-yolov8): Compare YOLO11 and YOLOv8 architectures, performance, use cases, and benchmarks. Discover which YOLO model fits your object detection needs.
- [YOLO11 vs YOLOv7](https://docs.ultralytics.com/compare/yolo11-vs-yolov7): Discover the key differences between YOLO11 and YOLOv7 in object detection. Compare architectures, benchmarks, and use cases to choose the best model.
- [YOLO11 vs YOLOv6](https://docs.ultralytics.com/compare/yolo11-vs-yolov6): Explore a detailed comparison of YOLO11 and YOLOv6-3.0, analyzing architectures, performance metrics, and use cases to choose the best object detection model.
- [YOLO11 vs YOLOv5](https://docs.ultralytics.com/compare/yolo11-vs-yolov5): Explore the comprehensive comparison between YOLO11 and YOLOv5. Learn about their architectures, performance metrics, use cases, and strengths.
- [YOLO11 vs RT-DETR](https://docs.ultralytics.com/compare/yolo11-vs-rtdetr): Compare RTDETRv2's accuracy with YOLO11's speed in this detailed analysis of top object detection models. Decide the best fit for your projects.
- [YOLO11 vs PP-YOLOE+](https://docs.ultralytics.com/compare/yolo11-vs-pp-yoloe): Compare YOLO11 and PP-YOLOE+ for object detection. Explore their performance, features, and use cases to choose the best model for your needs.
- [YOLO11 vs DAMO-YOLO](https://docs.ultralytics.com/compare/yolo11-vs-damo-yolo): Explore a detailed comparison of YOLO11 and DAMO-YOLO. Learn about their architectures, performance metrics, and use cases for object detection.
- [YOLO11 vs YOLOX](https://docs.ultralytics.com/compare/yolo11-vs-yolox): Explore YOLO11 and YOLOX, two leading object detection models. Compare architecture, performance, and use cases to select the best model for your needs.
- [YOLO11 vs EfficientDet](https://docs.ultralytics.com/compare/yolo11-vs-efficientdet): Explore a detailed technical comparison of YOLO11 and EfficientDet, including architecture, performance benchmarks, and ideal applications for object detection.
- [YOLOv10 vs YOLO26](https://docs.ultralytics.com/compare/yolov10-vs-yolo26): Explore a detailed technical comparison of YOLOv10 and YOLO26, including architecture, performance benchmarks, and ideal applications for object detection.
- [YOLOv10 vs YOLO11](https://docs.ultralytics.com/compare/yolov10-vs-yolo11): Explore a detailed comparison of YOLOv10 and YOLO11, two advanced object detection models. Understand their performance, strengths, and ideal use cases.
- [YOLOv10 vs YOLOv9](https://docs.ultralytics.com/compare/yolov10-vs-yolov9): Compare YOLOv10 and YOLOv9 object detection models. Explore architectures, metrics, and use cases to choose the best model for your application.
- [YOLOv10 vs YOLOv8](https://docs.ultralytics.com/compare/yolov10-vs-yolov8): Compare YOLOv10 and YOLOv8 for object detection. Discover differences in performance, architecture, and real-world applications to choose the best model.
- [YOLOv10 vs YOLOv7](https://docs.ultralytics.com/compare/yolov10-vs-yolov7): Compare YOLOv10 and YOLOv7 object detection models. Analyze performance, architecture, and use cases to choose the best fit for your AI project.
- [YOLOv10 vs YOLOv6](https://docs.ultralytics.com/compare/yolov10-vs-yolov6): Discover the key differences between YOLOv10 and YOLOv6-3.0, including architecture, performance benchmarks, and ideal use cases for object detection.
- [YOLOv10 vs YOLOv5](https://docs.ultralytics.com/compare/yolov10-vs-yolov5): Compare YOLOv10 and YOLOv5 models for object detection. Explore key features, performance metrics, strengths, and use cases to choose the right model.
- [YOLOv10 vs RT-DETR](https://docs.ultralytics.com/compare/yolov10-vs-rtdetr): Explore a detailed comparison of YOLOv10 and RTDETRv2. Discover their strengths, weaknesses, performance metrics, and ideal applications for object detection.
- [YOLOv10 vs PP-YOLOE+](https://docs.ultralytics.com/compare/yolov10-vs-pp-yoloe): Discover the key differences between YOLOv10 and PP-YOLOE+ with performance benchmarks, architecture insights, and ideal use cases for your projects.
- [YOLOv10 vs DAMO-YOLO](https://docs.ultralytics.com/compare/yolov10-vs-damo-yolo): Discover the key differences, performance benchmarks, and use cases of YOLOv10 and DAMO-YOLO in this detailed technical comparison.
- [YOLOv10 vs YOLOX](https://docs.ultralytics.com/compare/yolov10-vs-yolox): Compare YOLOv10 and YOLOX for object detection. Explore performance metrics, architecture, strengths, and ideal use cases for these top AI models.
- [YOLOv10 vs EfficientDet](https://docs.ultralytics.com/compare/yolov10-vs-efficientdet): Compare YOLOv10 and EfficientDet for object detection. Explore performance, use cases, and strengths to choose the best model for your needs.
- [YOLOv9 vs YOLO26](https://docs.ultralytics.com/compare/yolov9-vs-yolo26): Compare YOLOv9 and YOLO26 for object detection. Explore performance, architecture, and ideal use cases to choose the best model for your needs.
- [YOLOv9 vs YOLO11](https://docs.ultralytics.com/compare/yolov9-vs-yolo11): Compare YOLO11 and YOLOv9 for object detection. Explore innovations, benchmarks, and use cases to select the best model for your tasks.
- [YOLOv9 vs YOLOv10](https://docs.ultralytics.com/compare/yolov9-vs-yolov10): Explore a detailed technical comparison of YOLOv9 and YOLOv10, covering architecture, performance, and use cases. Find the best model for your needs.
- [YOLOv9 vs YOLOv8](https://docs.ultralytics.com/compare/yolov9-vs-yolov8): Discover the detailed technical comparison of YOLOv9 and YOLOv8. Explore their strengths, weaknesses, efficiency, and ideal use cases for object detection.
- [YOLOv9 vs YOLOv7](https://docs.ultralytics.com/compare/yolov9-vs-yolov7): Compare YOLOv9 and YOLOv7 for object detection. Explore their performance, architecture differences, strengths, and ideal applications.
- [YOLOv9 vs YOLOv6](https://docs.ultralytics.com/compare/yolov9-vs-yolov6): Compare YOLOv9 and YOLOv6-3.0 in architecture, performance, and applications. Discover the ideal model for your object detection needs.
- [YOLOv9 vs YOLOv5](https://docs.ultralytics.com/compare/yolov9-vs-yolov5): Compare YOLOv9 and YOLOv5 models for object detection. Explore their architecture, performance, use cases, and key differences to choose the best fit.
- [YOLOv9 vs RT-DETR](https://docs.ultralytics.com/compare/yolov9-vs-rtdetr): Compare YOLOv9 and RTDETRv2 for object detection. Explore speed, accuracy, use cases, and architectures to choose the best for your project.
- [YOLOv9 vs PP-YOLOE+](https://docs.ultralytics.com/compare/yolov9-vs-pp-yoloe): Compare YOLOv9 and PP-YOLOE+ models in architecture, performance, and use cases. Find the best object detection model for your needs.
- [YOLOv9 vs DAMO-YOLO](https://docs.ultralytics.com/compare/yolov9-vs-damo-yolo): Compare YOLOv9 and DAMO-YOLO. Discover their architecture, performance, strengths, and use cases to find the best fit for your object detection needs.
- [YOLOv9 vs YOLOX](https://docs.ultralytics.com/compare/yolov9-vs-yolox): Discover a detailed comparison of YOLOv9 and YOLOX, covering architectures, benchmarks, and use cases to help you choose the best object detection model.
- [YOLOv9 vs EfficientDet](https://docs.ultralytics.com/compare/yolov9-vs-efficientdet): Discover detailed insights comparing YOLOv9 and EfficientDet for object detection. Learn about their performance, architecture, and best use cases.
- [YOLOv8 vs YOLO26](https://docs.ultralytics.com/compare/yolov8-vs-yolo26): Compare YOLOv8 and YOLO26 for object detection. Explore their architectures, performance benchmarks, and ideal use cases to choose the best model.
- [YOLOv8 vs YOLO11](https://docs.ultralytics.com/compare/yolov8-vs-yolo11): Compare YOLOv8 and YOLO11 for object detection. Explore their performance, architecture, and best-use cases to find the right model for your needs.
- [YOLOv8 vs YOLOv10](https://docs.ultralytics.com/compare/yolov8-vs-yolov10): Compare Ultralytics YOLOv8 and YOLOv10. Explore key differences in architecture, efficiency, use cases, and find the perfect model for your needs.
- [YOLOv8 vs YOLOv9](https://docs.ultralytics.com/compare/yolov8-vs-yolov9): Compare YOLOv8 and YOLOv9 models for object detection. Explore their accuracy, speed, resources, and use cases to choose the best model for your needs.
- [YOLOv8 vs YOLOv7](https://docs.ultralytics.com/compare/yolov8-vs-yolov7): Explore a detailed comparison of YOLOv8 and YOLOv7 models. Learn their strengths, performance benchmarks, and ideal use cases for object detection.
- [YOLOv8 vs YOLOv6](https://docs.ultralytics.com/compare/yolov8-vs-yolov6): Explore a detailed technical comparison of YOLOv8 and YOLOv6-3.0. Learn about architecture, performance, and use cases for real-time object detection.
- [YOLOv8 vs YOLOv5](https://docs.ultralytics.com/compare/yolov8-vs-yolov5): Discover key differences between YOLOv8 and YOLOv5. Compare speed, accuracy, use cases, and more to choose the ideal model for your computer vision needs.
- [YOLOv8 vs RT-DETR](https://docs.ultralytics.com/compare/yolov8-vs-rtdetr): Explore the detailed comparison of YOLOv8 and RTDETRv2 models for object detection. Discover their architecture, performance, and best use cases.
- [YOLOv8 vs PP-YOLOE+](https://docs.ultralytics.com/compare/yolov8-vs-pp-yoloe): Discover the key differences between YOLOv8 and PP-YOLOE+ in this technical comparison. Learn which model suits your object detection needs best.
- [YOLOv8 vs DAMO-YOLO](https://docs.ultralytics.com/compare/yolov8-vs-damo-yolo): Compare YOLOv8 and DAMO-YOLO object detection models. Explore differences in performance, architecture, and applications to choose the best fit.
- [YOLOv8 vs YOLOX](https://docs.ultralytics.com/compare/yolov8-vs-yolox): Compare YOLOv8 and YOLOX models for object detection. Discover strengths, weaknesses, benchmarks, and choose the right model for your application.
- [YOLOv8 vs EfficientDet](https://docs.ultralytics.com/compare/yolov8-vs-efficientdet): Compare YOLOv8 and EfficientDet for object detection. Explore their architectures, performance benchmarks, and ideal use cases to choose the best model.
- [YOLOv7 vs YOLO26](https://docs.ultralytics.com/compare/yolov7-vs-yolo26): Compare YOLOv7 and YOLO26 for object detection. Explore their architectures, performance benchmarks, and ideal use cases to choose the best model.
- [YOLOv7 vs YOLO11](https://docs.ultralytics.com/compare/yolov7-vs-yolo11): Explore the strengths, benchmarks, and use cases of YOLO11 and YOLOv7 object detection models. Find the best fit for your project in this in-depth guide.
- [YOLOv7 vs YOLOv10](https://docs.ultralytics.com/compare/yolov7-vs-yolov10): Discover the key differences between YOLOv7 and YOLOv10, from architecture to performance benchmarks, to choose the optimal model for your needs.
- [YOLOv7 vs YOLOv9](https://docs.ultralytics.com/compare/yolov7-vs-yolov9): Explore the differences between YOLOv7 and YOLOv9. Compare architecture, performance, and use cases to choose the best model for object detection.
- [YOLOv7 vs YOLOv8](https://docs.ultralytics.com/compare/yolov7-vs-yolov8): Compare YOLOv7 and YOLOv8 for object detection. Explore performance, architecture, and use cases to choose the best model for your vision tasks.
- [YOLOv7 vs YOLOv6](https://docs.ultralytics.com/compare/yolov7-vs-yolov6): Explore YOLOv7 vs YOLOv6-3.0 for object detection. Compare architectures, benchmarks, and applications to select the best model for your project.
- [YOLOv7 vs YOLOv5](https://docs.ultralytics.com/compare/yolov7-vs-yolov5): Explore a detailed comparison of YOLOv7 and YOLOv5. Learn their key features, performance metrics, strengths, and use cases to choose the right model.
- [YOLOv7 vs RT-DETR](https://docs.ultralytics.com/compare/yolov7-vs-rtdetr): Compare YOLOv7 and RTDETRv2 for object detection. Explore architecture, performance, and use cases to pick the best model for your project.
- [YOLOv7 vs PP-YOLOE+](https://docs.ultralytics.com/compare/yolov7-vs-pp-yoloe): Compare YOLOv7 and PP-YOLOE+ for object detection. Explore their performance, architectures, and best use cases to select the ideal model for your needs.
- [YOLOv7 vs DAMO-YOLO](https://docs.ultralytics.com/compare/yolov7-vs-damo-yolo): Explore a detailed comparison of YOLOv7 and DAMO-YOLO, analyzing their architecture, performance, and best use cases for object detection projects.
- [YOLOv7 vs YOLOX](https://docs.ultralytics.com/compare/yolov7-vs-yolox): Explore YOLOv7 vs YOLOX in this detailed comparison. Learn their architectures, performance metrics, and best use cases for object detection.
- [YOLOv7 vs EfficientDet](https://docs.ultralytics.com/compare/yolov7-vs-efficientdet): Compare YOLOv7 and EfficientDet for object detection. Discover their performance, features, strengths, and use cases to choose the best model for your needs.
- [YOLOv6 vs YOLO26](https://docs.ultralytics.com/compare/yolov6-vs-yolo26): Compare YOLOv6-3.0 and YOLO26 for object detection. Discover their performance, features, strengths, and use cases to choose the best model for your needs.
- [YOLOv6 vs YOLO11](https://docs.ultralytics.com/compare/yolov6-vs-yolo11): Compare YOLO11 and YOLOv6-3.0 for object detection. Explore architectures, metrics, and use cases to choose the best model for your needs.
- [YOLOv6 vs YOLOv10](https://docs.ultralytics.com/compare/yolov6-vs-yolov10): Explore a detailed comparison of YOLOv10 and YOLOv6-3.0. Analyze their architectures, benchmarks, strengths, and use cases for your AI projects.
- [YOLOv6 vs YOLOv9](https://docs.ultralytics.com/compare/yolov6-vs-yolov9): Explore a detailed comparison of YOLOv6-3.0 vs YOLOv9, highlighting performance, architecture, metrics, and use cases to choose the best object detection model.
- [YOLOv6 vs YOLOv8](https://docs.ultralytics.com/compare/yolov6-vs-yolov8): Compare YOLOv6-3.0 and YOLOv8 for object detection. Explore their architectures, strengths, and use cases to choose the best fit for your project.
- [YOLOv6 vs YOLOv7](https://docs.ultralytics.com/compare/yolov6-vs-yolov7): Compare YOLOv6-3.0 and YOLOv7 models for object detection. Explore architecture, performance benchmarks, use cases, and find the best for your needs.
- [YOLOv6 vs YOLOv5](https://docs.ultralytics.com/compare/yolov6-vs-yolov5): Compare YOLOv5 and YOLOv6-3.0 models. Explore benchmarks, architectures, speed, and accuracy to choose the best object detection model for your needs.
- [YOLOv6 vs RT-DETR](https://docs.ultralytics.com/compare/yolov6-vs-rtdetr): Compare YOLOv6 and RTDETR for object detection. Explore their architectures, performances, and use cases to choose your optimal computer vision model.
- [YOLOv6 vs PP-YOLOE+](https://docs.ultralytics.com/compare/yolov6-vs-pp-yoloe): Compare YOLOv6-3.0 and PP-YOLOE+ models. Explore performance, architecture, and use cases to choose the best object detection model for your needs.
- [YOLOv6 vs DAMO-YOLO](https://docs.ultralytics.com/compare/yolov6-vs-damo-yolo): Discover a thorough technical comparison of YOLOv6-3.0 and DAMO-YOLO. Analyze architecture, performance, and use cases to pick the best object detection model.
- [YOLOv6 vs YOLOX](https://docs.ultralytics.com/compare/yolov6-vs-yolox): Compare YOLOv6-3.0 and YOLOX architectures, performance, and applications. Find the best object detection model for your computer vision needs.
- [YOLOv6 vs EfficientDet](https://docs.ultralytics.com/compare/yolov6-vs-efficientdet): Explore a detailed comparison of YOLOv6-3.0 and EfficientDet including benchmarks, architectures, and applications for optimal object detection model choice.
- [YOLOv5 vs YOLO26](https://docs.ultralytics.com/compare/yolov5-vs-yolo26): Explore a detailed comparison of YOLOv5 and YOLO26 including benchmarks, architectures, and applications for optimal object detection model choice.
- [YOLOv5 vs YOLO11](https://docs.ultralytics.com/compare/yolov5-vs-yolo11): Explore the ultimate comparison between YOLOv5 and YOLO11. Learn about their architecture, performance metrics, and ideal use cases for object detection.
- [YOLOv5 vs YOLOv10](https://docs.ultralytics.com/compare/yolov5-vs-yolov10): Explore a detailed YOLOv5 vs YOLOv10 comparison, analyzing architectures, performance, and ideal applications for cutting-edge object detection.
- [YOLOv5 vs YOLOv9](https://docs.ultralytics.com/compare/yolov5-vs-yolov9): Compare YOLOv5 and YOLOv9 - performance, architecture, and use cases. Find the best model for real-time object detection and computer vision tasks.
- [YOLOv5 vs YOLOv8](https://docs.ultralytics.com/compare/yolov5-vs-yolov8): Compare YOLOv5 and YOLOv8 for speed, accuracy, and versatility. Learn which Ultralytics model is best for your object detection and vision tasks.
- [YOLOv5 vs YOLOv7](https://docs.ultralytics.com/compare/yolov5-vs-yolov7): Discover the technical comparison between YOLOv5 and YOLOv7, covering architectures, benchmarks, strengths, and ideal use cases for object detection.
- [YOLOv5 vs YOLOv6](https://docs.ultralytics.com/compare/yolov5-vs-yolov6): Compare YOLOv5 and YOLOv6-3.0 object detection models. Explore their architecture, performance, and applications to choose the best fit for your needs.
- [YOLOv5 vs RT-DETR](https://docs.ultralytics.com/compare/yolov5-vs-rtdetr): Compare YOLOv5 and RTDETRv2 for object detection. Explore their architectures, performance metrics, strengths, and best use cases in computer vision.
- [YOLOv5 vs PP-YOLOE+](https://docs.ultralytics.com/compare/yolov5-vs-pp-yoloe): Compare YOLOv5 and PP-YOLOE+ object detection models. Explore their architecture, performance, and use cases to choose the best fit for your project.
- [YOLOv5 vs DAMO-YOLO](https://docs.ultralytics.com/compare/yolov5-vs-damo-yolo): Explore a detailed comparison of YOLOv5 and DAMO-YOLO, including architecture, accuracy, speed, and use cases for optimal object detection solutions.
- [YOLOv5 vs YOLOX](https://docs.ultralytics.com/compare/yolov5-vs-yolox): Compare YOLOv5 and YOLOX object detection models. Explore performance metrics, strengths, weaknesses, and use cases to choose the best fit for your needs.
- [YOLOv5 vs EfficientDet](https://docs.ultralytics.com/compare/yolov5-vs-efficientdet): Compare YOLOv5 and EfficientDet for object detection. Explore architecture, performance, strengths, and use cases to choose the right model.
- [RT-DETR vs YOLO26](https://docs.ultralytics.com/compare/rtdetr-vs-yolo26): Compare RTDETRv2 and YOLO26 for object detection. Explore architecture, performance, and use cases to pick the best model for your needs.
- [RT-DETR vs YOLO11](https://docs.ultralytics.com/compare/rtdetr-vs-yolo11): Explore the technical comparison of RTDETRv2 and YOLO11. Discover strengths, weaknesses, and ideal use cases to choose the best detection model.
- [RT-DETR vs YOLOv10](https://docs.ultralytics.com/compare/rtdetr-vs-yolov10): Compare RTDETRv2 and YOLOv10 for object detection. Explore their features, performance, and ideal applications to choose the best model for your project.
- [RT-DETR vs YOLOv9](https://docs.ultralytics.com/compare/rtdetr-vs-yolov9): Compare RTDETRv2 and YOLOv9 object detection models. Explore performance, strengths, weaknesses, and ideal use cases to make an informed decision.
- [RT-DETR vs YOLOv8](https://docs.ultralytics.com/compare/rtdetr-vs-yolov8): Compare RTDETRv2 and YOLOv8 for object detection. Explore architecture, performance, and use cases to select the best model for your needs.
- [RT-DETR vs YOLOv7](https://docs.ultralytics.com/compare/rtdetr-vs-yolov7): Compare RTDETRv2 and YOLOv7 for object detection. Explore their architecture, performance, and use cases to choose the best model for your needs.
- [RT-DETR vs YOLOv6](https://docs.ultralytics.com/compare/rtdetr-vs-yolov6): Explore an in-depth comparison of RTDETRv2 and YOLOv6-3.0. Learn about architecture, performance, and use cases to choose the right object detection model.
- [RT-DETR vs YOLOv5](https://docs.ultralytics.com/compare/rtdetr-vs-yolov5): Discover the key differences between YOLOv5 and RTDETRv2, from architecture to accuracy, and find the best object detection model for your project.
- [RT-DETR vs PP-YOLOE+](https://docs.ultralytics.com/compare/rtdetr-vs-pp-yoloe): Explore the key differences between RTDETRv2 and PP-YOLOE+, two leading object detection models. Compare architectures, performance, and use cases.
- [RT-DETR vs DAMO-YOLO](https://docs.ultralytics.com/compare/rtdetr-vs-damo-yolo): Discover a detailed comparison of RTDETRv2 and DAMO-YOLO for object detection. Learn about their performance, strengths, and ideal use cases.
- [RT-DETR vs YOLOX](https://docs.ultralytics.com/compare/rtdetr-vs-yolox): Compare RTDETRv2 & YOLOX object detection models. Discover their strengths, performance, and use cases to choose the best model for your project.
- [RT-DETR vs EfficientDet](https://docs.ultralytics.com/compare/rtdetr-vs-efficientdet): Explore RTDETRv2 vs EfficientDet for object detection with insights on architecture, performance, and use cases. Make an informed choice for your projects.
- [PP-YOLOE+ vs YOLO26](https://docs.ultralytics.com/compare/pp-yoloe-vs-yolo26): Compare PP-YOLOE+ and YOLO26 for object detection. Explore architecture, performance, strengths, and use cases to choose the right model.
- [PP-YOLOE+ vs YOLO11](https://docs.ultralytics.com/compare/pp-yoloe-vs-yolo11): Compare PP-YOLOE+ and YOLO11 object detection models. Explore performance, strengths, weaknesses, and ideal use cases to make informed choices.
- [PP-YOLOE+ vs YOLOv10](https://docs.ultralytics.com/compare/pp-yoloe-vs-yolov10): Explore a detailed technical comparison of YOLOv10 and PP-YOLOE+ object detection models. Learn their strengths, use cases, performance, and architecture.
- [PP-YOLOE+ vs YOLOv9](https://docs.ultralytics.com/compare/pp-yoloe-vs-yolov9): Explore the differences between PP-YOLOE+ and YOLOv9 with detailed architecture, performance benchmarks, and use case analysis for object detection.
- [PP-YOLOE+ vs YOLOv8](https://docs.ultralytics.com/compare/pp-yoloe-vs-yolov8): Compare PP-YOLOE+ and YOLOv8—two top object detection models. Discover their strengths, weaknesses, and ideal use cases for your applications.
- [PP-YOLOE+ vs YOLOv7](https://docs.ultralytics.com/compare/pp-yoloe-vs-yolov7): Explore a technical comparison of PP-YOLOE+ and YOLOv7 models, covering architecture, performance benchmarks, and best use cases for object detection.
- [PP-YOLOE+ vs YOLOv6](https://docs.ultralytics.com/compare/pp-yoloe-vs-yolov6): Discover the strengths, weaknesses, and performance metrics of PP-YOLOE+ and YOLOv6-3.0. Choose the best model for your object detection needs.
- [PP-YOLOE+ vs YOLOv5](https://docs.ultralytics.com/compare/pp-yoloe-vs-yolov5): Compare PP-YOLOE+ and YOLOv5 with insights into architecture, performance, and use cases. Discover the best object detection model for your needs.
- [PP-YOLOE+ vs RT-DETR](https://docs.ultralytics.com/compare/pp-yoloe-vs-rtdetr): Explore a detailed comparison of PP-YOLOE+ and RTDETRv2 object detection models, analyzing performance, accuracy, and use cases to guide your decision.
- [PP-YOLOE+ vs DAMO-YOLO](https://docs.ultralytics.com/compare/pp-yoloe-vs-damo-yolo): Compare PP-YOLOE+ and DAMO-YOLO for object detection. Learn their strengths, weaknesses, and performance metrics to choose the right model.
- [PP-YOLOE+ vs YOLOX](https://docs.ultralytics.com/compare/pp-yoloe-vs-yolox): Discover the key differences between PP-YOLOE+ and YOLOX models in architecture, performance, and applications for streamlined object detection.
- [PP-YOLOE+ vs EfficientDet](https://docs.ultralytics.com/compare/pp-yoloe-vs-efficientdet): Compare PP-YOLOE+ and EfficientDet for object detection. Explore architectures, benchmarks, and use cases to select the best model for your needs.
- [DAMO-YOLO vs YOLO26](https://docs.ultralytics.com/compare/damo-yolo-vs-yolo26): Compare DAMO-YOLO and YOLO26 for object detection. Explore architectures, benchmarks, and use cases to select the best model for your needs.
- [DAMO-YOLO vs YOLO11](https://docs.ultralytics.com/compare/damo-yolo-vs-yolo11): Compare Ultralytics YOLO11 and DAMO-YOLO models in performance, architecture, and use cases. Discover the best fit for your computer vision needs.
- [DAMO-YOLO vs YOLOv10](https://docs.ultralytics.com/compare/damo-yolo-vs-yolov10): Compare YOLOv10 and DAMO-YOLO object detection models. Explore architectures, performance metrics, and ideal use cases for your computer vision needs.
- [DAMO-YOLO vs YOLOv9](https://docs.ultralytics.com/compare/damo-yolo-vs-yolov9): Explore a detailed technical comparison between DAMO-YOLO and YOLOv9, covering architecture, performance, and use cases for object detection applications.
- [DAMO-YOLO vs YOLOv8](https://docs.ultralytics.com/compare/damo-yolo-vs-yolov8): Discover the key differences between DAMO-YOLO and YOLOv8. Compare accuracy, speed, architecture, and use cases to choose the best object detection model.
- [DAMO-YOLO vs YOLOv7](https://docs.ultralytics.com/compare/damo-yolo-vs-yolov7): Detailed comparison of DAMO-YOLO vs YOLOv7 for object detection. Analyze performance, architecture, and use cases to choose the best model for your needs.
- [DAMO-YOLO vs YOLOv6](https://docs.ultralytics.com/compare/damo-yolo-vs-yolov6): Compare DAMO-YOLO and YOLOv6-3.0 for object detection. Discover their architectures, performance, and use cases to choose the best model for your needs.
- [DAMO-YOLO vs YOLOv5](https://docs.ultralytics.com/compare/damo-yolo-vs-yolov5): Explore a detailed comparison of DAMO-YOLO and YOLOv5, covering architecture, performance, and use cases to help select the best model for your project.
- [DAMO-YOLO vs RT-DETR](https://docs.ultralytics.com/compare/damo-yolo-vs-rtdetr): Compare DAMO-YOLO and RTDETRv2 performance, accuracy, and use cases. Explore insights for efficient and high-accuracy object detection in real-time.
- [DAMO-YOLO vs PP-YOLOE+](https://docs.ultralytics.com/compare/damo-yolo-vs-pp-yoloe): Compare DAMO-YOLO and PP-YOLOE+ for object detection. Discover strengths, weaknesses, and use cases to choose the best model for your projects.
- [DAMO-YOLO vs YOLOX](https://docs.ultralytics.com/compare/damo-yolo-vs-yolox): Explore a detailed comparison of DAMO-YOLO and YOLOX, analyzing architecture, performance, and use cases for object detection applications.
- [DAMO-YOLO vs EfficientDet](https://docs.ultralytics.com/compare/damo-yolo-vs-efficientdet): Compare DAMO-YOLO and EfficientDet for object detection. Explore architectures, metrics, and use cases to select the right model for your needs.
- [YOLOX vs YOLO26](https://docs.ultralytics.com/compare/yolox-vs-yolo26): Compare YOLOX and YOLO26 for object detection. Explore architectures, metrics, and use cases to select the right model for your needs.
- [YOLOX vs YOLO11](https://docs.ultralytics.com/compare/yolox-vs-yolo11): Compare YOLO11 and YOLOX for object detection. Explore benchmarks, architectures, and use cases to choose the best model for your project.
- [YOLOX vs YOLOv10](https://docs.ultralytics.com/compare/yolox-vs-yolov10): Compare YOLOv10 and YOLOX for object detection. Explore architecture, benchmarks, and use cases to choose the best real-time detection model for your needs.
- [YOLOX vs YOLOv9](https://docs.ultralytics.com/compare/yolox-vs-yolov9): Compare YOLOX and YOLOv9 for object detection. Explore performance, architecture, and use cases to choose the best model for your vision tasks.
- [YOLOX vs YOLOv8](https://docs.ultralytics.com/compare/yolox-vs-yolov8): Compare YOLOX and YOLOv8 for object detection. Explore their strengths, weaknesses, and benchmarks to make the best model choice for your needs.
- [YOLOX vs YOLOv7](https://docs.ultralytics.com/compare/yolox-vs-yolov7): Discover the differences between YOLOX and YOLOv7, two top computer vision models. Learn about their architecture, performance, and ideal use cases.
- [YOLOX vs YOLOv6](https://docs.ultralytics.com/compare/yolox-vs-yolov6): Compare YOLOX and YOLOv6-3.0 for object detection. Learn about architecture, performance, and applications to choose the best model for your needs.
- [YOLOX vs YOLOv5](https://docs.ultralytics.com/compare/yolox-vs-yolov5): Explore a detailed technical comparison of YOLOX vs YOLOv5. Learn their differences in architecture, performance, and ideal applications for object detection.
- [YOLOX vs RT-DETR](https://docs.ultralytics.com/compare/yolox-vs-rtdetr): Discover the key differences between YOLOX and RTDETRv2. Compare performance, architecture, and use cases for optimal object detection model selection.
- [YOLOX vs PP-YOLOE+](https://docs.ultralytics.com/compare/yolox-vs-pp-yoloe): Compare YOLOX and PP-YOLOE+, two anchor-free object detection models. Explore performance, architecture, and use cases to choose the best fit.
- [YOLOX vs DAMO-YOLO](https://docs.ultralytics.com/compare/yolox-vs-damo-yolo): Compare YOLOX and DAMO-YOLO object detection models. Explore architecture, performance, use cases, and choose the best fit for your project.
- [YOLOX vs EfficientDet](https://docs.ultralytics.com/compare/yolox-vs-efficientdet): Compare YOLOX and EfficientDet for object detection. Explore architecture, performance, and use cases to pick the best model for your needs.
- [EfficientDet vs YOLO26](https://docs.ultralytics.com/compare/efficientdet-vs-yolo26): Compare EfficientDet and YOLO26 for object detection. Explore architecture, performance, and use cases to make an informed choice for your projects.
- [EfficientDet vs YOLO11](https://docs.ultralytics.com/compare/efficientdet-vs-yolo11): Explore a detailed comparison of YOLO11 and EfficientDet, analyzing architecture, performance, and use cases to guide your object detection model choice.
- [EfficientDet vs YOLOv10](https://docs.ultralytics.com/compare/efficientdet-vs-yolov10): Compare EfficientDet and YOLOv10 for object detection. Explore their architectures, performance, strengths, and use cases to find the ideal model.
- [EfficientDet vs YOLOv9](https://docs.ultralytics.com/compare/efficientdet-vs-yolov9): Compare EfficientDet and YOLOv9 models in accuracy, speed, and use cases. Learn which object detection model suits your vision project best.
- [EfficientDet vs YOLOv8](https://docs.ultralytics.com/compare/efficientdet-vs-yolov8): Compare EfficientDet vs YOLOv8 for object detection. Explore their architecture, performance, and ideal use cases to make an informed choice.
- [EfficientDet vs YOLOv7](https://docs.ultralytics.com/compare/efficientdet-vs-yolov7): Discover key differences between EfficientDet and YOLOv7 models. Explore architecture, performance, and use cases to choose the best object detection model.
- [EfficientDet vs YOLOv6](https://docs.ultralytics.com/compare/efficientdet-vs-yolov6): Explore EfficientDet and YOLOv6-3.0 in a detailed comparison covering architecture, accuracy, speed, and best use cases to choose the right model for your needs.
- [EfficientDet vs YOLOv5](https://docs.ultralytics.com/compare/efficientdet-vs-yolov5): Explore a detailed technical comparison of EfficientDet and YOLOv5. Learn their strengths, weaknesses, and ideal use cases for object detection.
- [EfficientDet vs RT-DETR](https://docs.ultralytics.com/compare/efficientdet-vs-rtdetr): Explore a detailed comparison of EfficientDet and RTDETRv2. Compare performance, architecture, and use cases to choose the right object detection model.
- [EfficientDet vs PP-YOLOE+](https://docs.ultralytics.com/compare/efficientdet-vs-pp-yoloe): Compare EfficientDet and PP-YOLOE+ for object detection. Explore architectures, performance, scalability, and real-world applications. Learn more now!.
- [EfficientDet vs DAMO-YOLO](https://docs.ultralytics.com/compare/efficientdet-vs-damo-yolo): Compare EfficientDet and DAMO-YOLO object detection models in terms of accuracy, speed, and efficiency for real-time and resource-constrained applications.
- [EfficientDet vs YOLOX](https://docs.ultralytics.com/compare/efficientdet-vs-yolox): Explore a detailed comparison of EfficientDet and YOLOX models. Learn about their architectures, performance, use cases, and which fits your needs best.

## Datasets
- [Datasets](https://docs.ultralytics.com/datasets): Explore Ultralytics' diverse datasets for vision tasks like detection, segmentation, semantic segmentation, classification, and more. Enhance your projects with high-quality annotated data.
- [Detection](https://docs.ultralytics.com/datasets/detect): Learn about dataset formats compatible with Ultralytics YOLO for robust object detection. Explore supported datasets and learn how to convert formats.
- [African-wildlife](https://docs.ultralytics.com/datasets/detect/african-wildlife): Train YOLO object detection models on the African Wildlife Dataset — 1,504 images across 4 classes (buffalo, elephant, rhino, zebra) with automatic download.
- [Argoverse](https://docs.ultralytics.com/datasets/detect/argoverse): Train YOLO object detection models on the Argoverse (Argoverse-HD) dataset — 54,446 autonomous-driving images across 8 classes, from a ring-front-center camera.
- [Brain-tumor](https://docs.ultralytics.com/datasets/detect/brain-tumor): Train YOLO26 object detection on the Ultralytics Brain Tumor dataset — 1,116 MRI/CT scans across 2 classes for medical imaging and early diagnosis.
- [COCO](https://docs.ultralytics.com/datasets/detect/coco): Explore the COCO dataset for object detection and segmentation. Learn about its structure, usage, pretrained models, and key features.
- [COCO8](https://docs.ultralytics.com/datasets/detect/coco8): Explore the Ultralytics COCO8 dataset, a versatile and manageable set of 8 images perfect for testing object detection models and training pipelines.
- [COCO8-Grayscale](https://docs.ultralytics.com/datasets/detect/coco8-grayscale): Explore the Ultralytics COCO8-Grayscale dataset, a versatile and manageable set of 8 images perfect for testing object detection models and training pipelines.
- [COCO8-Multispectral](https://docs.ultralytics.com/datasets/detect/coco8-multispectral): Explore the Ultralytics COCO8-Multispectral dataset, an enhanced version of COCO8 with interpolated spectral channels, ideal for testing multispectral object detection models and training pipelines.
- [COCO12-Formats](https://docs.ultralytics.com/datasets/detect/coco12-formats): Explore the Ultralytics COCO12-Formats dataset, a test dataset featuring 12 supported image formats (AVIF, BMP, DNG, HEIC, JP2, JPEG, JPG, MPO, PNG, TIF, TIFF, WebP) for validating image loading pipelines.
- [COCO128](https://docs.ultralytics.com/datasets/detect/coco128): Explore the Ultralytics COCO128 dataset, a versatile and manageable set of 128 images perfect for testing object detection models and training pipelines.
- [Construction-PPE](https://docs.ultralytics.com/datasets/detect/construction-ppe): Train YOLO26 on the Construction-PPE dataset — 1,416 images across 11 classes for detecting helmets, gloves, vests, boots, goggles, and missing safety gear.
- [GlobalWheat2020](https://docs.ultralytics.com/datasets/detect/globalwheat2020): Train YOLO26 on the Global Wheat Head Dataset — 3,422 train, 748 validation, and 1,276 test field images labeled with wheat head boxes for single-class detection.
- [HomeObjects-3K](https://docs.ultralytics.com/datasets/detect/homeobjects-3k): Train YOLO26 on HomeObjects-3K — 2,689 indoor images across 12 household classes like bed, sofa, TV, and laptop for smart home, robotics, and AR detection.
- [KITTI](https://docs.ultralytics.com/datasets/detect/kitti): Ultralytics KITTI is a 2D object detection dataset for autonomous driving with 7,481 annotated images across 8 classes like car, pedestrian, and cyclist.
- [LVIS](https://docs.ultralytics.com/datasets/detect/lvis): LVIS is a large-vocabulary object detection and instance segmentation dataset with 1,203 classes over ~160K COCO images. Train Ultralytics YOLO on LVIS.
- [Medical-pills](https://docs.ultralytics.com/datasets/detect/medical-pills): The Medical Pills dataset provides 115 labeled images across one class (pill) for training Ultralytics YOLO object detection models in pharmaceutical automation.
- [Objects365](https://docs.ultralytics.com/datasets/detect/objects365): Objects365 is a large-scale object detection dataset with 1,742,289 training and 80,000 validation images across 365 classes. Train Ultralytics YOLO on it.
- [OpenImagesV7](https://docs.ultralytics.com/datasets/detect/open-images-v7): Open Images V7 is a Google object detection dataset with 1,743,042 training and 41,620 validation images across 601 classes. Train Ultralytics YOLO on it.
- [RF100](https://docs.ultralytics.com/datasets/detect/roboflow-100): Explore the Roboflow 100 dataset featuring 100 diverse datasets designed to test object detection models across various domains, from healthcare to video games.
- [Signature](https://docs.ultralytics.com/datasets/detect/signature): The Ultralytics Signature Detection Dataset provides 143 training and 35 validation document images with one signature class for YOLO object detection models.
- [SKU-110K](https://docs.ultralytics.com/datasets/detect/sku-110k): SKU-110K is a single-class retail-shelf object detection dataset of 11,743 densely packed images (8,219 train / 588 val / 2,936 test) for training YOLO models.
- [TT100K](https://docs.ultralytics.com/datasets/detect/tt100k): Train YOLO26 traffic-sign detection on the Tsinghua-Tencent TT100K dataset - 16,817 street-view images spanning 221 sign categories, with automatic download.
- [VisDrone](https://docs.ultralytics.com/datasets/detect/visdrone): Train YOLO26 on the VisDrone-DET aerial dataset - 6,471 train, 548 val, and 1,610 test drone images across 10 object classes with automatic download.
- [VOC](https://docs.ultralytics.com/datasets/detect/voc): Train YOLO26 on the PASCAL VOC detection dataset - 16,551 training and 4,952 validation images across 20 object classes with automatic download.
- [xView](https://docs.ultralytics.com/datasets/detect/xview): Train YOLO26 on the xView satellite dataset - 1M+ object instances across 60 classes in 0.3 m WorldView-3 imagery with automatic GeoJSON-to-YOLO conversion.
- [Segmentation](https://docs.ultralytics.com/datasets/segment): Explore the supported dataset formats for Ultralytics YOLO and learn how to prepare and use datasets for training object segmentation models.
- [Carparts-seg](https://docs.ultralytics.com/datasets/segment/carparts-seg): Train Ultralytics YOLO segmentation models on Carparts-Seg — 3,833 annotated images across 23 car-part classes for automotive AI applications.
- [COCO](https://docs.ultralytics.com/datasets/segment/coco): Explore the COCO-Seg dataset, an extension of COCO with 123,287 segmentation-labeled images across 80 classes. Learn how to train YOLO models with COCO-Seg.
- [COCO8-seg](https://docs.ultralytics.com/datasets/segment/coco8-seg): Discover the versatile and manageable COCO8-Seg dataset by Ultralytics, an 8-image, ~1 MB segmentation set ideal for testing and debugging models.
- [COCO128-seg](https://docs.ultralytics.com/datasets/segment/coco128-seg): Discover the COCO128-Seg dataset by Ultralytics, a 128-image, ~7 MB instance segmentation dataset ideal for testing and training YOLO26 models.
- [Crack-seg](https://docs.ultralytics.com/datasets/segment/crack-seg): Train Ultralytics YOLO segmentation models on the Crack Segmentation Dataset — 4,029 annotated road and wall images for a single crack class.
- [Package-seg](https://docs.ultralytics.com/datasets/segment/package-seg): Train Ultralytics YOLO segmentation models on the Package Segmentation Dataset — 2,197 annotated images across a single package class for logistics AI.
- [Semantic Segmentation](https://docs.ultralytics.com/datasets/semantic): Learn how to prepare semantic segmentation datasets for Ultralytics YOLO, including PNG mask labels, dataset YAML fields, ignore labels, and supported datasets.
- [Cityscapes](https://docs.ultralytics.com/datasets/semantic/cityscapes): Train Ultralytics YOLO on Cityscapes — 2,975 training and 500 validation images across 19 urban classes for semantic segmentation of street scenes.
- [Cityscapes8](https://docs.ultralytics.com/datasets/semantic/cityscapes8): Explore the Ultralytics Cityscapes8 dataset, a compact set of 8 urban-scene images for testing semantic segmentation models and training pipelines.
- [ADE20K](https://docs.ultralytics.com/datasets/semantic/ade20k): Train Ultralytics YOLO on the ADE20K dataset — 20,210 training and 2,000 validation images across 150 scene-parsing classes for semantic segmentation.
- [Pose](https://docs.ultralytics.com/datasets/pose): Learn the Ultralytics YOLO format for pose estimation datasets — COCO-Pose, COCO8-Pose, Dog-Pose, Hand Keypoints, Tiger-Pose — and how to add your own.
- [COCO](https://docs.ultralytics.com/datasets/pose/coco): Explore the Ultralytics COCO-Pose dataset: 58,945 images with 156K+ annotated people and a 17-keypoint schema, for training YOLO26 pose estimation models.
- [COCO8-pose](https://docs.ultralytics.com/datasets/pose/coco8-pose): Explore the Ultralytics COCO8-Pose dataset: 8 images (4 train / 4 val) using a 17-keypoint schema, for pose estimation sanity checks with YOLO26.
- [Dog-pose](https://docs.ultralytics.com/datasets/pose/dog-pose): Explore the Ultralytics Dog-Pose dataset: 6,773 training and 1,703 validation images with 24 keypoints per dog, for canine pose estimation with YOLO26.
- [Hand-keypoints](https://docs.ultralytics.com/datasets/pose/hand-keypoints): Explore the Ultralytics Hand Keypoints dataset: 26,768 hand images with 21 keypoints each, for gesture recognition and pose estimation with YOLO26.
- [Tiger-pose](https://docs.ultralytics.com/datasets/pose/tiger-pose): Explore the Ultralytics Tiger-Pose dataset: 263 images (210 train / 53 val) with 12 keypoints per tiger, ideal for testing pose estimation pipelines.
- [Classification](https://docs.ultralytics.com/datasets/classify): Learn how to structure datasets for YOLO classification tasks. Detailed folder structure and usage examples for effective training.
- [Caltech 101](https://docs.ultralytics.com/datasets/classify/caltech101): Train YOLO image classification models on Caltech-101, a benchmark of 9,144 images across 101 object categories plus a background class, with automatic 80/20 splitting.
- [Caltech 256](https://docs.ultralytics.com/datasets/classify/caltech256): Train YOLO image classification models on Caltech-256, a benchmark of 30,607 images across 256 object categories plus a background class, with automatic 80/20 splitting.
- [CIFAR-10](https://docs.ultralytics.com/datasets/classify/cifar10): Train YOLO image classification models on CIFAR-10, a benchmark of 60,000 32x32 color images in 10 balanced classes with a predefined 50k/10k train/test split.
- [CIFAR-100](https://docs.ultralytics.com/datasets/classify/cifar100): Train YOLO image classification models on CIFAR-100, a benchmark of 60,000 32x32 color images in 100 classes grouped into 20 superclasses, split 50k/10k.
- [Fashion-MNIST](https://docs.ultralytics.com/datasets/classify/fashion-mnist): Train YOLO image classification models on Fashion-MNIST, a benchmark of 70,000 28x28 grayscale Zalando clothing images in 10 balanced classes, split 60k/10k.
- [ImageNet](https://docs.ultralytics.com/datasets/classify/imagenet): ImageNet (ILSVRC-2012) image classification dataset: 1,000 classes, 1.28M training images. Train Ultralytics YOLO classification models with data=imagenet.
- [ImageNet-10](https://docs.ultralytics.com/datasets/classify/imagenet10): ImageNet10 is a tiny 24-image subset of ImageNet across its first 10 classes, built by Ultralytics for fast CI tests, sanity checks, and pipeline validation.
- [Imagenette](https://docs.ultralytics.com/datasets/classify/imagenette): ImageNette is a 13,394-image subset of ImageNet with 10 easily distinguishable classes, ideal for fast image classification training, prototyping, and teaching.
- [Imagewoof](https://docs.ultralytics.com/datasets/classify/imagewoof): ImageWoof is a challenging 12,954-image subset of ImageNet with 10 dog breeds, built for fine-grained image classification training and benchmarking.
- [MNIST](https://docs.ultralytics.com/datasets/classify/mnist): Train YOLO image classification models on MNIST, a benchmark of 70,000 28x28 grayscale handwritten digit images in 10 classes, split 60k/10k.
- [OBB Datasets](https://docs.ultralytics.com/datasets/obb): Discover OBB dataset formats for Ultralytics YOLO models. Learn about their structure, application, and format conversions to enhance your object detection training.
- [DOTA8](https://docs.ultralytics.com/datasets/obb/dota8): Explore the DOTA8 dataset - a small, versatile oriented object detection dataset ideal for testing and debugging object detection models using Ultralytics YOLO26.
- [DOTA128](https://docs.ultralytics.com/datasets/obb/dota128): Explore the DOTA128 dataset - a versatile oriented object detection dataset ideal for testing and debugging OBB models using Ultralytics YOLO26.
- [DOTAv2](https://docs.ultralytics.com/datasets/obb/dota-v2): Explore the DOTA dataset for object detection in aerial images, featuring 1.7M Oriented Bounding Boxes across 18 categories. Ideal for aerial image analysis.
- [Multi-Object Tracking](https://docs.ultralytics.com/datasets/track): Learn how to use Multi-Object Tracking with YOLO. Explore dataset formats, tracking algorithms, and implementation examples using Python or CLI for real-time object tracking.

## Solutions
- [Solutions](https://docs.ultralytics.com/solutions): Explore Ultralytics Solutions using YOLO26 for object counting, blurring, security, and more. Enhance efficiency and solve real-world problems with cutting-edge AI.
- [Analytics](https://docs.ultralytics.com/guides/analytics): Build real-time line graphs, bar plots, pie charts, and area plots from YOLO26 object detection and tracking data in Python to visualize counts frame by frame.
- [Distance Calculation](https://docs.ultralytics.com/guides/distance-calculation): Learn how to calculate distances between objects using Ultralytics YOLO26 for accurate spatial positioning and scene understanding.
- [Heatmaps](https://docs.ultralytics.com/guides/heatmaps): Generate real-time object tracking heatmaps on video with the Ultralytics YOLO26 Heatmap solution to visualize traffic flow and crowd movement patterns.
- [Instance Segmentation Tracking](https://docs.ultralytics.com/guides/instance-segmentation-and-tracking): Master instance segmentation and tracking with Ultralytics YOLO26. Learn techniques for precise object identification and tracking.
- [Live Inference](https://docs.ultralytics.com/guides/streamlit-live-inference): Learn how to set up a real-time object detection application using Streamlit and Ultralytics YOLO26. Follow this step-by-step guide to implement webcam-based object detection.
- [Object Blurring](https://docs.ultralytics.com/guides/object-blurring): Automatically detect and blur objects in real time with Ultralytics YOLO26. Anonymize faces, license plates, and sensitive content with adjustable intensity.
- [Object Counting](https://docs.ultralytics.com/guides/object-counting): Count objects crossing a line or inside a region in real time with Ultralytics YOLO26. Track and tally specific classes for crowd analysis, retail, and traffic.
- [Object Counting in Regions](https://docs.ultralytics.com/guides/region-counting): Count objects in multiple user-defined polygonal zones of a video with the Ultralytics YOLO26 RegionCounter solution and read the counts in your code.
- [Object Cropping](https://docs.ultralytics.com/guides/object-cropping): Detect and crop objects from images and videos with Ultralytics YOLO26, saving each detection to disk for focused analysis and dataset building.
- [Parking Management](https://docs.ultralytics.com/guides/parking-management): Detect occupied and available parking spaces in real time with Ultralytics YOLO26. Track vehicles, monitor lot occupancy, and export annotated video.
- [Queue Management](https://docs.ultralytics.com/guides/queue-management): Learn how to manage and optimize queues using Ultralytics YOLO26 to reduce wait times and increase efficiency in various real-world applications.
- [Security Alarm System](https://docs.ultralytics.com/guides/security-alarm-system): Enhance your security with real-time object detection using Ultralytics YOLO26. Reduce false positives and integrate seamlessly with existing systems.
- [Similarity Search](https://docs.ultralytics.com/guides/similarity-search): Build a semantic image search engine with OpenAI CLIP and Flask. Embed images, run natural-language queries, and serve ranked results from a web app with the Ultralytics Python package.
- [Speed Estimation](https://docs.ultralytics.com/guides/speed-estimation): Estimate the speed of tracked objects in video with Ultralytics YOLO26 using frame rate and pixel-to-meter scaling for traffic and surveillance use cases.
- [Track Objects in Zone](https://docs.ultralytics.com/guides/trackzone): Discover how TrackZone leverages Ultralytics YOLO26 to precisely track objects within specific zones, enabling real-time insights for crowd analysis, surveillance, and targeted monitoring.
- [VisionEye View Objects Mapping](https://docs.ultralytics.com/guides/vision-eye): Discover VisionEye's object mapping and tracking powered by Ultralytics YOLO26. Simulate human eye precision, track objects, and calculate distances effortlessly.
- [Workouts Monitoring](https://docs.ultralytics.com/guides/workouts-monitoring): Optimize your fitness routine with real-time workouts monitoring using Ultralytics YOLO26. Track and improve your exercise form and performance.

## Guides
- [Guides](https://docs.ultralytics.com/guides): Master YOLO with Ultralytics tutorials covering training, deployment and optimization. Find solutions, improve metrics, and deploy with ease.
- [AzureML Quickstart](https://docs.ultralytics.com/guides/azureml-quickstart): Learn how to run YOLO26 on AzureML. Quickstart instructions for terminal and notebooks to harness Azure's cloud computing for efficient model training.
- [Best Practices for Model Deployment](https://docs.ultralytics.com/guides/model-deployment-practices): Best practices for deploying YOLO26: choose cloud, edge, or local environments, optimize with pruning and quantization, and secure your deployed models.
- [COCO to YOLO Conversion](https://docs.ultralytics.com/guides/coco-to-yolo): Convert COCO JSON annotations to YOLO format for object detection, instance segmentation, and pose estimation, with class ID mapping for custom datasets.
- [COCO JSON Training](https://docs.ultralytics.com/guides/coco-json-training): Train Ultralytics YOLO directly on COCO JSON annotations without converting to YOLO format. Custom dataset and trainer example with complete working code for detection training.
- [Conda Quickstart](https://docs.ultralytics.com/guides/conda-quickstart): Install Ultralytics YOLO with Conda. Set up an isolated conda-forge environment, add CUDA GPU support, run the Conda Docker image, and speed up installs with the libmamba solver.
- [Customizing Trainer](https://docs.ultralytics.com/guides/custom-trainer): Learn how to customize the Ultralytics YOLO trainer with custom metrics, class-weighted loss, custom model saving, backbone freezing, per-layer learning rates, SyncBatchNorm, and gradient clipping.
- [Data Collection and Annotation](https://docs.ultralytics.com/guides/data-collection-and-annotation): Learn data collection and annotation for computer vision: set up classes, source unbiased data, choose annotation types and formats, and run quality control.
- [DeepStream on NVIDIA Jetson](https://docs.ultralytics.com/guides/deepstream-nvidia-jetson): Learn how to deploy Ultralytics YOLO26 on NVIDIA Jetson devices using TensorRT and DeepStream SDK. Explore performance benchmarks and maximize AI capabilities.
- [DL Streamer on Intel](https://docs.ultralytics.com/guides/dlstreamer-intel): Learn how to deploy Ultralytics YOLO26 on Intel Core Ultra Series 3 platforms using DL Streamer Pipeline Framework and OpenVINO™ for optimized inference.
- [Define CV Project Goals](https://docs.ultralytics.com/guides/defining-project-goals): Define your computer vision project with a 4-step problem statement, SMART measurable objectives, and the right task, model, and deployment choices.
- [YOLO on Vertex AI](https://docs.ultralytics.com/guides/vertex-ai-deployment-with-docker): Learn how to deploy pretrained YOLO26 models on Google Cloud Vertex AI using Docker containers and FastAPI for scalable inference with complete control over preprocessing and postprocessing.
- [Docker Quickstart](https://docs.ultralytics.com/guides/docker-quickstart): Learn to effortlessly set up Ultralytics in Docker, from installation to running with CPU/GPU support. Follow our comprehensive guide for seamless container experience.
- [Edge TPU on Raspberry Pi](https://docs.ultralytics.com/guides/coral-edge-tpu-on-raspberry-pi): Accelerate Ultralytics YOLO26 inference on a Raspberry Pi with the Coral Edge TPU. Step-by-step guide to install the runtime, export to Edge TPU format, and run fast low-power inference.
- [End-to-End Detection](https://docs.ultralytics.com/guides/end2end-detection): Learn how YOLO26 end-to-end NMS-free detection works, what changes in your deployment pipeline, which export formats support it, and how to migrate.
- [Export Non-YOLO Models](https://docs.ultralytics.com/guides/export-non-yolo-models): Export any PyTorch model (timm, torchvision, or custom) to ONNX, OpenVINO, CoreML, TensorFlow, and more through one Ultralytics API, with no per-backend code.
- [Fine-Tuning YOLO on Custom Data](https://docs.ultralytics.com/guides/finetuning-guide): Fine-tune YOLO26 on a custom dataset using pretrained weights. Covers transfer learning, layer freezing, optimizers, two-stage training, and fixing low mAP.
- [Hyperparameter Tuning](https://docs.ultralytics.com/guides/hyperparameter-tuning): Tune Ultralytics YOLO hyperparameters with model.tune() and a genetic algorithm. Define a search space, run iterations, and find settings that maximize fitness.
- [Model Evaluation and Fine-Tuning](https://docs.ultralytics.com/guides/model-evaluation-insights): Learn how to evaluate YOLO26 models with metrics like mAP and IoU, then fine-tune them in Python to boost detection accuracy on your own dataset.
- [Isolating Segmentation Objects](https://docs.ultralytics.com/guides/isolating-segmentation-objects): Learn how to isolate and extract segmented objects from Ultralytics YOLO inference results with OpenCV. Remove backgrounds, crop to objects, and save transparent PNGs step by step.
- [K-Fold Cross Validation](https://docs.ultralytics.com/guides/kfold-cross-validation): Learn to implement K-Fold Cross Validation for object detection datasets using Ultralytics YOLO. Improve your model's reliability and robustness.
- [Knowledge Distillation 🚀](https://docs.ultralytics.com/guides/knowledge-distillation): Master knowledge distillation for Ultralytics YOLO to optimize student model performance with a teacher model.
- [Maintaining Your Computer Vision Model](https://docs.ultralytics.com/guides/model-monitoring-and-maintenance): Understand the key practices for monitoring, maintaining, and documenting computer vision models to guarantee accuracy, spot anomalies, and mitigate data drift.
- [Modal Quickstart](https://docs.ultralytics.com/guides/modal-quickstart): Run Ultralytics YOLO26 on Modal's serverless cloud. This quickstart covers authentication, GPU inference, and training jobs with persistent storage.
- [Model Deployment Options](https://docs.ultralytics.com/guides/model-deployment-options): Learn about YOLO26's diverse deployment options to maximize your model's performance. Explore PyTorch, TensorRT, OpenVINO, LiteRT, and more!
- [Model Testing](https://docs.ultralytics.com/guides/model-testing): Learn how to test computer vision models on unseen data, run YOLO26 validation and prediction on your test set, and catch overfitting and data leakage.
- [Model YAML Configuration Guide](https://docs.ultralytics.com/guides/model-yaml-config): Learn how to structure and customize model architectures using Ultralytics YAML configuration files. Master module definitions, connections, and scaling parameters.
- [NVIDIA DALI GPU Preprocessing](https://docs.ultralytics.com/guides/nvidia-dali): Use NVIDIA DALI to run YOLO letterbox resize, padding, and normalization on the GPU, removing CPU preprocessing bottlenecks in TensorRT and Triton deployments.
- [NVIDIA DGX Spark](https://docs.ultralytics.com/guides/nvidia-dgx-spark): Learn to deploy Ultralytics YOLO26 on NVIDIA DGX Spark with our detailed guide. Explore performance benchmarks and maximize AI capabilities on this compact desktop AI supercomputer.
- [NVIDIA Jetson](https://docs.ultralytics.com/guides/nvidia-jetson): Learn to deploy Ultralytics YOLO26 on NVIDIA Jetson devices with our detailed guide. Explore performance benchmarks and maximize AI capabilities.
- [OpenVINO Latency vs Throughput modes](https://docs.ultralytics.com/guides/optimizing-openvino-latency-vs-throughput-modes): Discover how to enhance Ultralytics YOLO model performance using Intel's OpenVINO toolkit. Boost latency and throughput efficiently.
- [Preprocessing Annotated Data](https://docs.ultralytics.com/guides/preprocessing-annotated-data): Preprocess annotated computer vision data with YOLO26: resize, normalize, augment, and split datasets to boost training accuracy and reduce overfitting.
- [Raspberry Pi](https://docs.ultralytics.com/guides/raspberry-pi): Deploy Ultralytics YOLO26 on Raspberry Pi 4 and 5 with install steps, NCNN export for fastest inference, camera setup, and benchmarks across ten formats.
- [ROS Quickstart](https://docs.ultralytics.com/guides/ros-quickstart): Integrate Ultralytics YOLO with ROS Noetic to run object detection and segmentation on RGB images, depth images, and point clouds for robotic perception.
- [SAHI Tiled Inference](https://docs.ultralytics.com/guides/sahi-tiled-inference): Learn how to implement YOLO26 with SAHI for sliced inference. Optimize memory usage and enhance detection accuracy for large-scale applications.
- [Steps of a Computer Vision Project](https://docs.ultralytics.com/guides/steps-of-a-cv-project): Discover essential steps for launching a successful computer vision project, from defining goals to model deployment and maintenance.
- [Tips for Model Training](https://docs.ultralytics.com/guides/model-training-tips): Train YOLO computer vision models more efficiently with proven tips on batch size, mixed precision, caching, early stopping, and optimizer choice.
- [Triton Inference Server](https://docs.ultralytics.com/guides/triton-inference-server): Learn how to integrate Ultralytics YOLO26 with NVIDIA Triton Inference Server for scalable, high-performance AI model deployment.
- [Viewing Inference Images in a Terminal](https://docs.ultralytics.com/guides/view-results-in-terminal): Display YOLO inference results directly in a VSCode terminal with the sixel protocol on Linux and macOS, ideal for remote SSH sessions and headless machines without a GUI.
- [YOLO26 Training Recipe](https://docs.ultralytics.com/guides/yolo26-training-recipe): Learn how YOLO26 models were trained on COCO, including optimizer settings, augmentation pipelines, loss weights, and fine-tuning guidance for each model size.
- [YOLO Architecture Explained](https://docs.ultralytics.com/guides/yolo-architecture): Understand how the YOLO architecture evolved from YOLOv3 to YOLO26 across the backbone, neck, and detection head, including anchor-free and NMS-free design.
- [YOLO Common Issues](https://docs.ultralytics.com/guides/yolo-common-issues): Troubleshoot common YOLO26 issues — installation and CUDA errors, slow training, prediction problems, and model export failures — with tested fixes.
- [YOLO Data Augmentation](https://docs.ultralytics.com/guides/yolo-data-augmentation): Learn about essential data augmentation techniques in Ultralytics YOLO. Explore various transformations, their impacts, and how to implement them effectively for improved model performance.
- [YOLO Performance Metrics](https://docs.ultralytics.com/guides/yolo-performance-metrics): Explore essential YOLO26 performance metrics like mAP, IoU, F1 Score, Precision, and Recall. Learn how to calculate and interpret them for model evaluation.
- [YOLO Thread-Safe Inference](https://docs.ultralytics.com/guides/yolo-thread-safe-inference): Learn how to ensure thread-safe YOLO model inference in Python. Avoid race conditions and run your multi-threaded tasks reliably with best practices.
- [Explorer](https://docs.ultralytics.com/datasets/explorer): Discover Ultralytics Explorer for semantic search, SQL queries, vector similarity, and natural language dataset exploration.
- [Explorer API](https://docs.ultralytics.com/datasets/explorer/api): Explore the Ultralytics Explorer API for dataset exploration with SQL queries, vector similarity search, and semantic search. Learn installation and usage tips.
- [Explorer Dashboard Demo](https://docs.ultralytics.com/datasets/explorer/dashboard): Unlock advanced data exploration with Ultralytics Explorer GUI. Utilize semantic search, run SQL queries, and ask AI for natural language data insights.
- [VOC Exploration Example](https://docs.ultralytics.com/datasets/explorer/explorer): Dive into advanced data exploration with Ultralytics Explorer. Perform semantic searches, execute SQL queries, and leverage AI-powered natural language insights for seamless data analysis.
- [YOLOv5](https://docs.ultralytics.com/yolov5): Explore comprehensive Ultralytics YOLOv5 documentation with step-by-step tutorials on training, deployment, and model optimization. Empower your vision projects today!
- [Quickstart](https://docs.ultralytics.com/yolov5/quickstart-tutorial): Kickstart your real-time object detection journey with Ultralytics YOLOv5! This guide covers installation, inference, and training to help you master YOLOv5 quickly.
- [Amazon Web Services (AWS)](https://docs.ultralytics.com/yolov5/environments/aws-quickstart-tutorial): Discover how to set up and run Ultralytics YOLOv5 on AWS Deep Learning Instances. Follow our comprehensive guide to get started quickly and cost-effectively.
- [Google Cloud (GCP)](https://docs.ultralytics.com/yolov5/environments/google-cloud-quickstart-tutorial): Master Ultralytics YOLOv5 deployment on Google Cloud Platform Deep Learning VM. Perfect for AI beginners and experts to achieve high-performance object detection.
- [AzureML](https://docs.ultralytics.com/yolov5/environments/azureml-quickstart-tutorial): Learn how to set up and run Ultralytics YOLOv5 on AzureML. Follow this quickstart guide for easy configuration and model training on an AzureML compute instance.
- [Docker Image](https://docs.ultralytics.com/yolov5/environments/docker-image-quickstart-tutorial): Learn how to set up and run YOLOv5 in a Docker container with step-by-step instructions for CPU and GPU environments, mounting volumes, and using display servers.
- [Train Custom Data](https://docs.ultralytics.com/yolov5/tutorials/train-custom-data): Learn how to train YOLOv5 on your own custom datasets with easy-to-follow steps. Detailed guide on dataset preparation, model selection, and training process.
- [Tips for Best Training Results](https://docs.ultralytics.com/yolov5/tutorials/tips-for-best-training-results): Discover how to achieve optimal mAP and training results using YOLOv5. Learn essential dataset, model selection, and training settings best practices.
- [Multi-GPU Training](https://docs.ultralytics.com/yolov5/tutorials/multi-gpu-training): Learn how to train YOLOv5 on multiple GPUs for optimal performance. Guide covers single and multiple machine setups with DistributedDataParallel.
- [PyTorch Hub](https://docs.ultralytics.com/yolov5/tutorials/pytorch-hub-model-loading): Learn how to load YOLOv5 from PyTorch Hub for seamless model inference and customization. Follow our step-by-step guide at Ultralytics Docs.
- [ONNX, CoreML, TensorRT Export](https://docs.ultralytics.com/yolov5/tutorials/model-export): Learn to export YOLOv5 models to various formats like TFLite, ONNX, CoreML and TensorRT. Increase model efficiency and deployment flexibility with our step-by-step guide.
- [Test-Time Augmentation (TTA)](https://docs.ultralytics.com/yolov5/tutorials/test-time-augmentation): Boost your YOLOv5 performance with Test-Time Augmentation (TTA). Learn setup, testing, and inference techniques to elevate mAP and Recall.
- [Model Ensembling](https://docs.ultralytics.com/yolov5/tutorials/model-ensembling): Learn how to use YOLOv5 model ensembling during testing and inference to enhance mAP and Recall for more accurate predictions.
- [Pruning/Sparsity Tutorial](https://docs.ultralytics.com/yolov5/tutorials/model-pruning-and-sparsity): Learn how to prune YOLOv5 models for improved performance. Follow this step-by-step guide to optimize your YOLOv5 models effectively.
- [Hyperparameter evolution](https://docs.ultralytics.com/yolov5/tutorials/hyperparameter-evolution): Learn how to optimize YOLOv5 hyperparameters using genetic algorithms for improved training performance. Step-by-step instructions included.
- [Transfer learning with frozen layers](https://docs.ultralytics.com/yolov5/tutorials/transfer-learning-with-frozen-layers): Learn to freeze YOLOv5 layers for efficient transfer learning, reducing resources and speeding up training while maintaining accuracy.
- [Architecture Summary](https://docs.ultralytics.com/yolov5/tutorials/architecture-description): Dive deep into the powerful YOLOv5 architecture by Ultralytics, exploring its model structure, data augmentation techniques, training strategies, and loss computations.
- [Neural Magic's DeepSparse](https://docs.ultralytics.com/yolov5/tutorials/neural-magic-pruning-quantization): Learn how to deploy YOLOv5 using Neural Magic's DeepSparse for GPU-class performance on CPUs. Discover easy integration, flexible deployments, and more.
- [Comet Logging](https://docs.ultralytics.com/yolov5/tutorials/comet-logging-integration): Learn to track, visualize and optimize YOLOv5 model metrics with Comet for seamless machine learning workflows.
- [Clearml Logging](https://docs.ultralytics.com/yolov5/tutorials/clearml-logging-integration): Learn how to use ClearML for tracking YOLOv5 experiments, data versioning, hyperparameter optimization, and remote execution with ease.

## Integrations
- [Integrations](https://docs.ultralytics.com/integrations): Discover Ultralytics integrations for streamlined ML workflows, dataset management, optimized model training, and robust deployment solutions.
- [Albumentations](https://docs.ultralytics.com/integrations/albumentations): Learn how to use Albumentations with YOLO26 to enhance data augmentation, improve model performance, and streamline your computer vision projects.
- [Amazon SageMaker](https://docs.ultralytics.com/integrations/amazon-sagemaker): Learn step-by-step how to deploy Ultralytics' YOLO26 on Amazon SageMaker Endpoints, from setup to testing, for powerful real-time inference with AWS services.
- [Ambarella](https://docs.ultralytics.com/integrations/ambarella): Deploy Ultralytics YOLO models on Ambarella CVflow SoCs like the CV72 with SpongeTorch compression-aware training, ONNX export, and CVflow toolchain compilation.
- [Axelera](https://docs.ultralytics.com/integrations/axelera): Deploy Ultralytics YOLO models on Axelera AI's Metis hardware. Learn how to export, compile, and run high-performance edge inference with up to 856 TOPS.
- [ClearML](https://docs.ultralytics.com/integrations/clearml): Discover how to integrate YOLO26 with ClearML to streamline your MLOps workflow, automate experiments, and enhance model management effortlessly.
- [Comet ML](https://docs.ultralytics.com/integrations/comet): Learn to simplify the logging of YOLO26 training with Comet. This guide covers installation, setup, real-time insights, and custom logging.
- [Core AI](https://docs.ultralytics.com/integrations/coreai): Learn about Apple's Core AI framework and .aimodel format, how Core AI differs from Core ML, and the planned Ultralytics integration.
- [CoreML](https://docs.ultralytics.com/integrations/coreml): Export Ultralytics YOLO26 models to CoreML for fast on-device inference on the Apple Neural Engine across iPhone, iPad, and Mac. Step-by-step export, quantization, and deployment guide.
- [DEEPX](https://docs.ultralytics.com/integrations/deepx): Learn how to export Ultralytics YOLO models to DEEPX format for efficient deployment on DEEPX NPU hardware with INT8 quantization and high-performance edge inference.
- [DVC](https://docs.ultralytics.com/integrations/dvc): Unlock seamless YOLO26 tracking with DVCLive. Discover how to log, visualize, and analyze experiments for optimized ML model performance.
- [ExecuTorch](https://docs.ultralytics.com/integrations/executorch): Export YOLO26 models to ExecuTorch format for efficient on-device inference on mobile and edge devices. Optimize your AI models for iOS, Android, and embedded systems.
- [Google Colab](https://docs.ultralytics.com/integrations/google-colab): Learn how to efficiently train Ultralytics YOLO26 models using Google Colab's powerful cloud-based environment. Start your project with ease.
- [Gradio](https://docs.ultralytics.com/integrations/gradio): Discover an interactive way to perform object detection with Ultralytics YOLO26 using Gradio. Upload images and adjust settings for real-time results.
- [Hailo](https://docs.ultralytics.com/integrations/hailo): Convert selected Ultralytics YOLO models from ONNX to Hailo HEF for Hailo-8, Hailo-8L, Raspberry Pi AI Kit, AI HAT+, Hailo-10, and Hailo-15 devices.
- [IBM Watsonx](https://docs.ultralytics.com/integrations/ibm-watsonx): Dive into our detailed integration guide on using IBM Watson to train a YOLO26 model. Uncover key features and step-by-step instructions on model training.
- [JupyterLab](https://docs.ultralytics.com/integrations/jupyterlab): Learn how to use JupyterLab to train and experiment with Ultralytics YOLO26 models. Discover key features, setup instructions, and solutions to common issues.
- [Kaggle](https://docs.ultralytics.com/integrations/kaggle): Learn how to use Kaggle to train Ultralytics YOLO26 models with free GPU/TPU resources. Discover Kaggle's features, benefits, and best practices for efficient model development.
- [LiteRT](https://docs.ultralytics.com/integrations/litert): Convert Ultralytics YOLO models to LiteRT (formerly TensorFlow Lite) for fast on-device inference on mobile, embedded, edge, and browser platforms from a single .tflite model.
- [MLflow](https://docs.ultralytics.com/integrations/mlflow): Learn how to set up and use MLflow logging with Ultralytics YOLO for enhanced experiment tracking, model reproducibility, and performance improvements.
- [MNN](https://docs.ultralytics.com/integrations/mnn): Optimize YOLO26 models for mobile and embedded devices by exporting to MNN format. Learn how to convert, deploy, and run inference with MNN.
- [NCNN](https://docs.ultralytics.com/integrations/ncnn): Optimize YOLO26 models for mobile and embedded devices by exporting to NCNN format. Enhance performance in resource-constrained environments.
- [Neptune](https://docs.ultralytics.com/integrations/neptune): Integrate Neptune with Ultralytics YOLO26 to track experiments, visualize metrics, log model checkpoints, and organize training metadata.
- [Neural Magic](https://docs.ultralytics.com/integrations/neural-magic): Enhance YOLO26 performance using Neural Magic's DeepSparse Engine. Learn how to deploy and benchmark YOLO26 models on CPUs for efficient object detection.
- [ONNX](https://docs.ultralytics.com/integrations/onnx): Learn how to export YOLO26 models to ONNX format for flexible deployment across various platforms with enhanced performance.
- [OpenVINO](https://docs.ultralytics.com/integrations/openvino): Learn to export YOLO26 models to OpenVINO format for up to 3x CPU speedup and hardware acceleration on Intel GPU and NPU.
- [PaddlePaddle](https://docs.ultralytics.com/integrations/paddlepaddle): Learn how to export YOLO26 models to PaddlePaddle format for enhanced performance, flexibility, and deployment across various platforms and devices.
- [Paperspace Gradient](https://docs.ultralytics.com/integrations/paperspace): Simplify YOLO26 training with Paperspace Gradient's all-in-one MLOps platform. Access GPUs, automate workflows, and deploy with ease.
- [Qualcomm QNN](https://docs.ultralytics.com/integrations/qnn): Export Ultralytics YOLO models to Qualcomm QNN for fast on-device inference on Snapdragon Hexagon NPU, Adreno GPU, and CPU. Step-by-step Qualcomm Snapdragon export guide.
- [Ray Tune](https://docs.ultralytics.com/integrations/ray-tune): Optimize YOLO26 model performance with Ray Tune. Learn efficient hyperparameter tuning using advanced search strategies, parallelism, and early stopping.
- [Roboflow](https://docs.ultralytics.com/integrations/roboflow): Learn how to label data and export datasets in YOLO format using Roboflow for training Ultralytics models.
- [Rockchip RKNN](https://docs.ultralytics.com/integrations/rockchip-rknn): Learn how to export YOLO26 models to RKNN format, including floating-point and INT8 quantized models, for efficient deployment on Rockchip platforms.
- [Seeed Studio reCamera](https://docs.ultralytics.com/integrations/seeedstudio-recamera): Discover how to get started with Seeed Studio reCamera for edge AI applications using Ultralytics YOLO26. Learn about its powerful features, real-world applications, and how to export YOLO26 models to ONNX format for seamless integration.
- [SONY IMX500](https://docs.ultralytics.com/integrations/sony-imx500): Learn to export Ultralytics YOLO11 models to Sony's IMX500 format for efficient edge AI deployment on Raspberry Pi AI Camera with on-chip processing.
- [TensorBoard](https://docs.ultralytics.com/integrations/tensorboard): Learn how to integrate YOLO26 with TensorBoard for real-time visual insights into your model's training metrics, performance graphs, and debugging workflows.
- [TensorRT](https://docs.ultralytics.com/integrations/tensorrt): Learn to convert YOLO26 models to TensorRT for high-speed NVIDIA GPU inference. Boost efficiency and deploy optimized models with our step-by-step guide.
- [TF GraphDef](https://docs.ultralytics.com/integrations/tf-graphdef): Learn how to export YOLO26 models to the TF GraphDef format for seamless deployment on various platforms, including mobile and web.
- [TF SavedModel](https://docs.ultralytics.com/integrations/tf-savedmodel): Learn how to export Ultralytics YOLO26 models to TensorFlow SavedModel format for easy deployment across various platforms and environments.
- [TF.js (deprecated)](https://docs.ultralytics.com/integrations/tfjs): Convert your Ultralytics YOLO26 models to TensorFlow.js for high-speed, local object detection. Learn how to optimize ML models for browser and Node.js apps.
- [TFLite (deprecated)](https://docs.ultralytics.com/integrations/tflite): Historical guide to legacy YOLO TFLite model export and edge deployment. Use LiteRT for new exports.
- [TFLite Edge TPU](https://docs.ultralytics.com/integrations/edge-tpu): Learn how to export YOLO26 models to TFLite Edge TPU format for high-speed, low-power inferencing on mobile and embedded devices.
- [TorchScript](https://docs.ultralytics.com/integrations/torchscript): Learn how to export Ultralytics YOLO26 models to TorchScript for flexible, cross-platform deployment. Boost performance and utilize in various environments.
- [VS Code](https://docs.ultralytics.com/integrations/vscode): An overview of how the Ultralytics-Snippets extension for Visual Studio Code can help developers accelerate their work with the Ultralytics Python package.
- [Weights & Biases](https://docs.ultralytics.com/integrations/weights-biases): Learn how to enhance YOLO26 experiment tracking and visualization with Weights & Biases for better model performance and management.

## Platform
- [Platform](https://docs.ultralytics.com/platform): Ultralytics Platform is an end-to-end computer vision platform for data preparation, model training, and deployment with multi-region infrastructure.
- [Quickstart](https://docs.ultralytics.com/platform/quickstart): Get started with Ultralytics Platform in minutes. Learn to create an account, upload datasets, train YOLO models, and deploy to production.
- [Data](https://docs.ultralytics.com/platform/data): Learn about data management in Ultralytics Platform including dataset upload, annotation tools, and statistics visualization for YOLO model training.
- [Datasets](https://docs.ultralytics.com/platform/data/datasets): Learn how to upload, manage, and organize datasets in Ultralytics Platform for YOLO model training with automatic processing and statistics.
- [Annotation](https://docs.ultralytics.com/platform/data/annotation): Learn to annotate images in Ultralytics Platform with manual tools, skeleton templates for pose estimation, and Smart annotation with SAM and YOLO models for detect, segment, semantic, and OBB tasks.
- [Train](https://docs.ultralytics.com/platform/train): Learn about model training in Ultralytics Platform including project organization, cloud training, and real-time metrics streaming.
- [Projects](https://docs.ultralytics.com/platform/train/projects): Learn how to organize and manage projects in Ultralytics Platform for efficient model development.
- [Models](https://docs.ultralytics.com/platform/train/models): Learn how to manage, analyze, and export trained models in Ultralytics Platform with support for 19+ deployment formats.
- [Cloud Training](https://docs.ultralytics.com/platform/train/cloud-training): Learn how to train YOLO models on cloud GPUs with Ultralytics Platform, including remote training and real-time metrics streaming.
- [Deploy](https://docs.ultralytics.com/platform/deploy): Learn about model deployment options in Ultralytics Platform including inference testing, dedicated endpoints, and monitoring dashboards.
- [Inference](https://docs.ultralytics.com/platform/deploy/inference): Learn how to test YOLO models with the Ultralytics Platform inference API including browser testing and programmatic access.
- [Endpoints](https://docs.ultralytics.com/platform/deploy/endpoints): Deploy YOLO models to dedicated endpoints in 43 global regions with scale-to-zero behavior and monitoring on Ultralytics Platform.
- [Monitoring](https://docs.ultralytics.com/platform/deploy/monitoring): Monitor deployed YOLO models on Ultralytics Platform with real-time metrics, request logs, and performance dashboards.
- [Integrations](https://docs.ultralytics.com/platform/integrations): Connect Ultralytics Platform to existing tools, cloud storage, and Enterprise On Premise compute and datasets.
- [Ultralytics HUB](https://docs.ultralytics.com/platform/integrations/ultralytics-hub): Import your datasets, projects, models, and account balance from Ultralytics HUB into Ultralytics Platform with a single API key.
- [Roboflow](https://docs.ultralytics.com/platform/integrations/roboflow): Import every dataset from your Roboflow workspace into Ultralytics Platform with a single API key.
- [Google Cloud Storage](https://docs.ultralytics.com/platform/integrations/google-cloud-storage): Connect Google Cloud Storage to Ultralytics Platform and train YOLO models on images in your GCS buckets without uploading a copy.
- [Amazon S3](https://docs.ultralytics.com/platform/integrations/amazon-s3): Connect Amazon S3 to Ultralytics Platform and train YOLO models on images in your S3 buckets without uploading a copy.
- [Azure Blob Storage](https://docs.ultralytics.com/platform/integrations/azure-blob-storage): Connect Azure Blob Storage to Ultralytics Platform and train YOLO models on images in your Azure containers without uploading a copy.
- [On Premise](https://docs.ultralytics.com/platform/integrations/on-premise): Use local datasets and train YOLO models on your own computer without uploading images or model files to the cloud.
- [Account](https://docs.ultralytics.com/platform/account): Manage your Ultralytics Platform account including API keys, billing, and user settings with security and GDPR compliance.
- [API Keys](https://docs.ultralytics.com/platform/account/api-keys): Create and manage API keys for Ultralytics Platform with secure AES-256-GCM encryption for remote training and programmatic access.
- [Teams](https://docs.ultralytics.com/platform/account/teams): Create and manage teams on Ultralytics Platform with role-based access control, shared resources, and enterprise features for collaborative computer vision workflows.
- [Billing](https://docs.ultralytics.com/platform/account/billing): Manage credits, payments, and subscriptions on Ultralytics Platform with transparent pricing for cloud training and deployments.
- [Activity](https://docs.ultralytics.com/platform/account/activity): Track all account activity and events on Ultralytics Platform with the activity feed, including training, uploads, and system events.
- [Trash](https://docs.ultralytics.com/platform/account/trash): Learn how to recover deleted projects, datasets, and models from Trash on Ultralytics Platform with the 30-day soft delete policy.
- [Settings](https://docs.ultralytics.com/platform/account/settings): Configure your Ultralytics Platform profile, preferences, and data settings with GDPR-compliant data export and deletion options.
- [Explore](https://docs.ultralytics.com/platform/explore): Discover public datasets and projects on the Ultralytics Platform Explore page. Browse, search, and clone community content for computer vision and YOLO.
- [REST API](https://docs.ultralytics.com/platform/api): Complete REST API reference for Ultralytics Platform including authentication, endpoints, and examples for datasets, models, and deployments.

## Rust Inference
- [Rust Inference](https://docs.ultralytics.com/inference): Ultralytics Inference for Rust is a high-performance YOLO inference library and CLI built on ONNX Runtime, with GPU acceleration and zero Python runtime.

## Reference
- [Reference](https://docs.ultralytics.com/reference): Browse the Ultralytics Python API reference, auto-generated from source for cfg, data, engine, hub, models, nn, optim, solutions, trackers, and utils.
- [__init__](https://docs.ultralytics.com/reference/__init__): Learn how Ultralytics uses lazy imports with __getattr__ to speed up package startup and load model classes like YOLO, NAS, RTDETR, and SAM only when needed.
- [__init__](https://docs.ultralytics.com/reference/cfg/__init__): Explore the methods for managing and validating YOLO configurations in the Ultralytics configuration module. Enhance your YOLO experience.
- [annotator](https://docs.ultralytics.com/reference/data/annotator): Explore Ultralytics' annotator script for automatic image annotation using YOLO and SAM models. Contribute to improve it on GitHub.
- [augment](https://docs.ultralytics.com/reference/data/augment): Explore Ultralytics image augmentation techniques like MixUp, Mosaic, and Random Perspective for enhancing model training. Improve your deep learning models now.
- [base](https://docs.ultralytics.com/reference/data/base): Explore the Ultralytics BaseDataset class for efficient image loading and processing with custom transformations and caching options.
- [build](https://docs.ultralytics.com/reference/data/build): Explore the functionality and examples of data builders like InfiniteDataLoader and various YOLO dataset builders in Ultralytics.
- [converter](https://docs.ultralytics.com/reference/data/converter): Explore comprehensive data conversion tools for YOLO models including COCO, DOTA, and YOLO bbox2segment converters.
- [dataset](https://docs.ultralytics.com/reference/data/dataset): Explore the YOLODataset and its subclasses for object detection, segmentation, and multi-modal tasks. Find details on dataset loading, caching, and augmentation.
- [loaders](https://docs.ultralytics.com/reference/data/loaders): Explore detailed documentation on Ultralytics data loaders including SourceTypes, LoadStreams, and more. Enhance your ML workflows with our comprehensive guides.
- [split](https://docs.ultralytics.com/reference/data/split): Learn how to split datasets into train, validation, and test subsets using Ultralytics utilities for efficient data preparation.
- [split_dota](https://docs.ultralytics.com/reference/data/split_dota): Learn how to utilize the ultralytics.data.split_dota module to process and split DOTA datasets efficiently. Explore detailed functions and examples.
- [utils](https://docs.ultralytics.com/reference/data/utils): Explore in-depth reference for utility functions in Ultralytics data module. Learn about image verification, dataset handling, and more.
- [exporter](https://docs.ultralytics.com/reference/engine/exporter): Learn how to export YOLOv8 models to formats like ONNX, TensorRT, CoreML, and more. Optimize your exports for different platforms.
- [model](https://docs.ultralytics.com/reference/engine/model): Explore the base class for implementing YOLO models with unified APIs for training, validation, prediction, and more. Learn how to utilize different task types and model configurations.
- [predictor](https://docs.ultralytics.com/reference/engine/predictor): Discover how to use the Base Predictor class in the Ultralytics YOLO engine for efficient image and video inference.
- [results](https://docs.ultralytics.com/reference/engine/results): Explore the details of Ultralytics engine results including classes like BaseTensor, Results, Boxes, Masks, Keypoints, Probs, and OBB to handle inference results efficiently.
- [trainer](https://docs.ultralytics.com/reference/engine/trainer): Learn how to use BaseTrainer in Ultralytics YOLO for efficient model training. Comprehensive guide for configurations, datasets, and optimization.
- [tuner](https://docs.ultralytics.com/reference/engine/tuner): Optimize YOLO model performance using Ultralytics Tuner. Learn about systematic hyperparameter tuning for object detection, segmentation, classification, and tracking.
- [validator](https://docs.ultralytics.com/reference/engine/validator): Explore Ultralytics BaseValidator for model validation in PyTorch, TensorFlow, ONNX, and more. Learn to check model accuracy and performance metrics.
- [__init__](https://docs.ultralytics.com/reference/hub/__init__): Explore Ultralytics Platform API functions for login, logout, model reset, export, and dataset checks. Enhance your YOLO workflows with these essential utilities.
- [auth](https://docs.ultralytics.com/reference/hub/auth): Learn how to manage API key and cookie-based authentication in Ultralytics with the Auth class. Step-by-step guide for effective authentication.
- [__init__](https://docs.ultralytics.com/reference/hub/google/__init__): Reference for the GCPRegions class in Ultralytics, which provides functionality for testing and analyzing latency across Google Cloud Platform regions.
- [session](https://docs.ultralytics.com/reference/hub/session): Explore the HUBTrainingSession class for managing Ultralytics YOLO model training, heartbeats, and checkpointing.
- [utils](https://docs.ultralytics.com/reference/hub/utils): Explore the utilities in the Ultralytics Platform. Learn about smart_request, request_with_credentials, and more to enhance your YOLO projects.
- [__init__](https://docs.ultralytics.com/reference/models/__init__): Reference for `ultralytics.models.__init__` in the Ultralytics package.
- [model](https://docs.ultralytics.com/reference/models/fastsam/model): Discover how to use the FastSAM model with Ultralytics. Learn about its interface and implementation details with practical examples.
- [predict](https://docs.ultralytics.com/reference/models/fastsam/predict): Explore the Fast SAM Predictor in the Ultralytics YOLO framework. Learn about its segmentation prediction tasks, configuration, and post-processing steps.
- [utils](https://docs.ultralytics.com/reference/models/fastsam/utils): Explore the utility functions in FastSAM for adjusting bounding boxes and calculating IoU, benefiting computer vision projects.
- [val](https://docs.ultralytics.com/reference/models/fastsam/val): Discover FastSAM Validator for segmentation in Ultralytics YOLO. Learn how to validate with custom metrics and avoid common errors. Contribute on GitHub.
- [model](https://docs.ultralytics.com/reference/models/nas/model): Explore the YOLO-NAS model interface and learn how to utilize pretrained YOLO-NAS models for object detection with Ultralytics.
- [predict](https://docs.ultralytics.com/reference/models/nas/predict): Learn about NASPredictor in Ultralytics YOLO for efficient object detection. Explore its attributes, methods, and usage with examples.
- [val](https://docs.ultralytics.com/reference/models/nas/val): Explore the Ultralytics NASValidator for efficient YOLO model validation. Learn about NMS and post-processing configurations.
- [model](https://docs.ultralytics.com/reference/models/rtdetr/model): Explore the interface for Baidu's RT-DETR, a Vision Transformer-based real-time object detector in the Ultralytics Docs. Learn more about its efficient hybrid encoding and IoU-aware query selection.
- [predict](https://docs.ultralytics.com/reference/models/rtdetr/predict): Access the complete reference for the RTDETRPredictor class in Ultralytics. Learn about its attributes, methods, and example usage for real-time object detection.
- [train](https://docs.ultralytics.com/reference/models/rtdetr/train): Explore RTDETRTrainer for efficient real-time object detection leveraging Vision Transformers. Learn configuration, dataset handling, and advanced model training.
- [val](https://docs.ultralytics.com/reference/models/rtdetr/val): Explore the RTDETRValidator and RTDETRDataset classes for real-time detection and tracking. Understand initialization, transformations, and post-processing.
- [amg](https://docs.ultralytics.com/reference/models/sam/amg): Explore the detailed API reference for Ultralytics SAM/AMG models, including functions for mask stability scores, crop box generation, and more.
- [build](https://docs.ultralytics.com/reference/models/sam/build): Discover detailed instructions for building various Segment Anything Model (SAM) and Segment Anything Model 2 (SAM 2) architectures with Ultralytics, including SAM ViT and Mobile-SAM.
- [build_sam3](https://docs.ultralytics.com/reference/models/sam/build_sam3): Explore the ultralytics.models.sam.build_sam3 module for building SAM3 image models, including backbone and transformer components.
- [model](https://docs.ultralytics.com/reference/models/sam/model): Explore the SAM (Segment Anything Model) and SAM 2 (Segment Anything Model 2) interface for real-time image segmentation. Learn about promptable segmentation and zero-shot capabilities.
- [blocks](https://docs.ultralytics.com/reference/models/sam/modules/blocks): Explore detailed documentation of various SAM and SAM 2 modules such as MaskDownSampler, CXBlock, and more, available in Ultralytics' repository.
- [decoders](https://docs.ultralytics.com/reference/models/sam/modules/decoders): Explore the MaskDecoder and MLP modules in Ultralytics for efficient mask prediction using transformer architecture. Detailed attributes, functionalities, and implementation.
- [encoders](https://docs.ultralytics.com/reference/models/sam/modules/encoders): Explore detailed documentation of various SAM encoder modules such as ImageEncoderViT, PromptEncoder, and more, available in Ultralytics' repository.
- [memory_attention](https://docs.ultralytics.com/reference/models/sam/modules/memory_attention): Explore detailed documentation of various SAM 2 encoder modules such as MemoryAttentionLayer, MemoryAttention, available in Ultralytics' repository.
- [sam](https://docs.ultralytics.com/reference/models/sam/modules/sam): Discover the Ultralytics SAM and SAM 2 module for object segmentation. Learn about its components, such as image encoders and mask decoders, in this comprehensive guide.
- [tiny_encoder](https://docs.ultralytics.com/reference/models/sam/modules/tiny_encoder): Explore the detailed implementation of TinyViT architecture including Conv2d_BN, PatchEmbed, MBConv, and more in Ultralytics.
- [transformer](https://docs.ultralytics.com/reference/models/sam/modules/transformer): Explore the TwoWayTransformer module in Ultralytics, designed for simultaneous attention to image and query points. Ideal for object detection and segmentation tasks.
- [utils](https://docs.ultralytics.com/reference/models/sam/modules/utils): Explore the detailed API reference for Ultralytics SAM and SAM 2 models.
- [predict](https://docs.ultralytics.com/reference/models/sam/predict): Explore Ultralytics SAM and SAM 2 Predictor for advanced, real-time image segmentation using the Segment Anything Model (SAM and SAM 2). Complete implementation details and auxiliary utilities.
- [decoder](https://docs.ultralytics.com/reference/models/sam/sam3/decoder): Explore the ultralytics.models.sam.sam3.decoder module, including transformer decoder layers used in SAM3 model heads.
- [encoder](https://docs.ultralytics.com/reference/models/sam/sam3/encoder): Explore the ultralytics.models.sam.sam3.encoder module, including transformer encoder layers and fusion blocks for SAM3.
- [geometry_encoders](https://docs.ultralytics.com/reference/models/sam/sam3/geometry_encoders): Explore the ultralytics.models.sam.sam3.geometry_encoders module for prompt and geometry encoding utilities used by SAM3.
- [maskformer_segmentation](https://docs.ultralytics.com/reference/models/sam/sam3/maskformer_segmentation): Explore the ultralytics.models.sam.sam3.maskformer_segmentation module for segmentation heads and predictors used with SAM3.
- [model_misc](https://docs.ultralytics.com/reference/models/sam/sam3/model_misc): Explore the ultralytics.models.sam.sam3.model_misc module with helper layers and utilities used in SAM3 model components.
- [necks](https://docs.ultralytics.com/reference/models/sam/sam3/necks): Explore the ultralytics.models.sam.sam3.necks module for SAM3 neck components that connect vision backbones to downstream heads.
- [sam3_image](https://docs.ultralytics.com/reference/models/sam/sam3/sam3_image): Explore the ultralytics.models.sam.sam3.sam3_image module, including the SAM3SemanticModel and related output helpers.
- [text_encoder_ve](https://docs.ultralytics.com/reference/models/sam/sam3/text_encoder_ve): Explore the ultralytics.models.sam.sam3.text_encoder_ve module for SAM3 text-encoder components used in vision-language pipelines.
- [vitdet](https://docs.ultralytics.com/reference/models/sam/sam3/vitdet): Explore the ultralytics.models.sam.sam3.vitdet module for ViTDet building blocks used as vision backbones in SAM3.
- [vl_combiner](https://docs.ultralytics.com/reference/models/sam/sam3/vl_combiner): Explore the ultralytics.models.sam.sam3.vl_combiner module for combining vision and language features in SAM3.
- [loss](https://docs.ultralytics.com/reference/models/utils/loss): Explore detailed implementations of loss functions for DETR and RT-DETR models in Ultralytics.
- [ops](https://docs.ultralytics.com/reference/models/utils/ops): Explore the utilities and operations in Ultralytics models like HungarianMatcher and get_cdn_group. Learn how to optimize and manage model operations efficiently.
- [predict](https://docs.ultralytics.com/reference/models/yolo/classify/predict): Learn about the ClassificationPredictor class for YOLO models at Ultralytics. Get details on initialization, preprocessing, and postprocessing for classification tasks.
- [train](https://docs.ultralytics.com/reference/models/yolo/classify/train): Explore the train.py module in Ultralytics YOLO for efficient classification model training. Learn more with examples and detailed code documentation.
- [val](https://docs.ultralytics.com/reference/models/yolo/classify/val): Explore the source code and functionalities of the YOLO Classification Validator in Ultralytics for evaluating classification models effectively.
- [predict](https://docs.ultralytics.com/reference/models/yolo/detect/predict): Explore the Ultralytics YOLO Detection Predictor. Learn how to implement and use the DetectionPredictor class for object detection in Python.
- [train](https://docs.ultralytics.com/reference/models/yolo/detect/train): Learn about the DetectionTrainer class for training YOLO models on custom datasets. Discover methods, examples, and more.
- [val](https://docs.ultralytics.com/reference/models/yolo/detect/val): Explore the DetectionValidator class for YOLO models in Ultralytics. Learn validation techniques, metrics, and dataset handling for object detection.
- [model](https://docs.ultralytics.com/reference/models/yolo/model): Explore the ultralytics.models.yolo.model module for YOLO object detection. Learn initialization, model mapping, and more.
- [predict](https://docs.ultralytics.com/reference/models/yolo/obb/predict): Learn how to use the Ultralytics YOLO OBBPredictor for oriented bounding box predictions. Enhance your object detection models with ease.
- [train](https://docs.ultralytics.com/reference/models/yolo/obb/train): Explore the Ultralytics YOLO OBB Trainer class for efficient training with Oriented Bounding Box models. Learn with examples and method details.
- [val](https://docs.ultralytics.com/reference/models/yolo/obb/val): Explore the OBBValidator for YOLO, an advanced class for oriented bounding boxes (OBB). Learn initialization, processes, and evaluation methods.
- [predict](https://docs.ultralytics.com/reference/models/yolo/pose/predict): Learn about the PosePredictor class for YOLO model predictions on pose data. Get setup instructions, example usage, and implementation details.
- [train](https://docs.ultralytics.com/reference/models/yolo/pose/train): Explore the PoseTrainer class for training pose models using YOLO from Ultralytics. Includes initialization, model configuration, and plotting methods.
- [val](https://docs.ultralytics.com/reference/models/yolo/pose/val): Explore the PoseValidator class for YOLO models. Learn how to extend DetectionValidator for pose validation with example code and detailed methods.
- [predict](https://docs.ultralytics.com/reference/models/yolo/segment/predict): Understand the SegmentationPredictor class for segmentation-based predictions using YOLO. Learn more about its implementation and example usage.
- [train](https://docs.ultralytics.com/reference/models/yolo/segment/train): Learn how to train YOLO models for segmentation tasks with Ultralytics. Explore the SegmentationTrainer class and its functionalities.
- [val](https://docs.ultralytics.com/reference/models/yolo/segment/val): Explore the YOLO Segmentation Validator module for validating segment models. Understand its usage, metrics, and implementation within the Ultralytics framework.
- [predict](https://docs.ultralytics.com/reference/models/yolo/semantic/predict): Reference for YOLO semantic segmentation predictor. Learn about the SemanticSegmentationPredictor class and its inference methods.
- [train](https://docs.ultralytics.com/reference/models/yolo/semantic/train): Reference for YOLO semantic segmentation trainer. Learn about the SemanticSegmentationTrainer class and its training methods.
- [val](https://docs.ultralytics.com/reference/models/yolo/semantic/val): Reference for YOLO semantic segmentation validator. Learn about the SemanticSegmentationValidator class and its validation metrics.
- [train](https://docs.ultralytics.com/reference/models/yolo/world/train): Learn how to train a World Model with Ultralytics YOLO using advanced techniques and customizable options for optimal performance.
- [train_world](https://docs.ultralytics.com/reference/models/yolo/world/train_world): Explore the WorldTrainerFromScratch in YOLO for open-set datasets. Learn how to build, train, and evaluate models efficiently.
- [val](https://docs.ultralytics.com/reference/models/yolo/world/val): Reference for `ultralytics.models.yolo.world.val` in the Ultralytics package.
- [predict](https://docs.ultralytics.com/reference/models/yolo/yoloe/predict): Documentation for YOLOE visual prompt predictors in Ultralytics, supporting inference with visual prompts for both object detection and segmentation models.
- [train](https://docs.ultralytics.com/reference/models/yolo/yoloe/train): Learn about YOLOE training classes in Ultralytics, including standard, linear probing, and visual prompt training for detection and segmentation models.
- [train_seg](https://docs.ultralytics.com/reference/models/yolo/yoloe/train_seg): Documentation for YOLOE segmentation trainer classes in Ultralytics, supporting different training approaches including standard training, linear probing, training from scratch, and visual prompt training.
- [val](https://docs.ultralytics.com/reference/models/yolo/yoloe/val): Documentation for YOLOE validator classes in Ultralytics, supporting both text and visual prompt embeddings for object detection and segmentation models.
- [autobackend](https://docs.ultralytics.com/reference/nn/autobackend): Get to know more about Ultralytics nn.autobackend.check_class_names functionality. Optimize your YOLO models seamlessly.
- [axelera](https://docs.ultralytics.com/reference/nn/backends/axelera): Explore AxeleraBackend for Axelera hardware inference, deploying YOLO models on Axelera AI accelerators with optimized performance.
- [base](https://docs.ultralytics.com/reference/nn/backends/base): Explore the BaseBackend class, the abstract foundation for all inference backends in Ultralytics, defining the interface for model loading and inference.
- [coreml](https://docs.ultralytics.com/reference/nn/backends/coreml): Explore CoreMLBackend for Apple CoreML inference, enabling efficient YOLO model deployment on iOS, macOS, and Apple Silicon devices.
- [deepx](https://docs.ultralytics.com/reference/nn/backends/deepx): Reference for the Ultralytics DeepXBackend. Learn how to run inference with DEEPX NPU compiled models using the DX-Runtime.
- [executorch](https://docs.ultralytics.com/reference/nn/backends/executorch): Explore ExecuTorchBackend for Meta ExecuTorch inference, enabling efficient PyTorch model deployment on mobile and edge devices.
- [litert](https://docs.ultralytics.com/reference/nn/backends/litert): Explore LiteRTBackend for Google LiteRT (formerly TensorFlow Lite) inference with .tflite models, supporting FP32 and INT8 on mobile, edge, and browser targets.
- [mnn](https://docs.ultralytics.com/reference/nn/backends/mnn): Explore MNNBackend for Alibaba MNN inference, enabling lightweight and efficient model deployment on mobile and edge devices.
- [ncnn](https://docs.ultralytics.com/reference/nn/backends/ncnn): Explore NCNNBackend for Tencent NCNN inference, optimized for mobile and embedded platforms with Vulkan acceleration support.
- [onnx](https://docs.ultralytics.com/reference/nn/backends/onnx): Explore ONNXBackend and ONNXIMXBackend for Microsoft ONNX Runtime inference, supporting standard ONNX models and NXP IMX-optimized variants.
- [openvino](https://docs.ultralytics.com/reference/nn/backends/openvino): Explore OpenVINOBackend for optimized inference on Intel hardware, supporting OpenVINO IR models for efficient deployment on CPUs, GPUs, and VPUs.
- [paddle](https://docs.ultralytics.com/reference/nn/backends/paddle): Explore PaddleBackend for Baidu PaddlePaddle inference, supporting deployment with Paddle Inference engine on various hardware platforms.
- [pytorch](https://docs.ultralytics.com/reference/nn/backends/pytorch): Explore PyTorchBackend and TorchScriptBackend for native PyTorch and TorchScript model inference in Ultralytics YOLO models.
- [qnn](https://docs.ultralytics.com/reference/nn/backends/qnn): Reference for the Ultralytics QNNBackend. Learn how to run inference with Qualcomm QNN context-binary models using ONNX Runtime's QNN Execution Provider.
- [rknn](https://docs.ultralytics.com/reference/nn/backends/rknn): Explore RKNNBackend for Rockchip RKNN inference, enabling optimized YOLO deployment on Rockchip NPU-equipped edge devices.
- [tensorflow](https://docs.ultralytics.com/reference/nn/backends/tensorflow): Explore TensorFlowBackend for Google TensorFlow inference including SavedModel, GraphDef, TFLite, and Edge TPU formats.
- [tensorrt](https://docs.ultralytics.com/reference/nn/backends/tensorrt): Explore TensorRTBackend for high-performance GPU inference with NVIDIA TensorRT, optimizing YOLO models for production deployment.
- [triton](https://docs.ultralytics.com/reference/nn/backends/triton): Explore TritonBackend for NVIDIA Triton Inference Server, enabling scalable cloud and edge deployment of YOLO models.
- [distill_model](https://docs.ultralytics.com/reference/nn/distill_model): Reference for `ultralytics.nn.distill_model` in the Ultralytics package.
- [activation](https://docs.ultralytics.com/reference/nn/modules/activation): Explore activation functions in Ultralytics, including the Unified activation function and other custom implementations for neural networks.
- [block](https://docs.ultralytics.com/reference/nn/modules/block): Explore detailed documentation of block modules in Ultralytics, available for deep learning tasks. Contribute and improve the codebase.
- [conv](https://docs.ultralytics.com/reference/nn/modules/conv): Explore detailed documentation on convolution modules like Conv, LightConv, GhostConv, and more used in Ultralytics models.
- [head](https://docs.ultralytics.com/reference/nn/modules/head): Explore docs covering Ultralytics YOLO detection, pose & RTDETRDecoder. Comprehensive guides to help you understand Ultralytics nn modules.
- [transformer](https://docs.ultralytics.com/reference/nn/modules/transformer): Learn about Ultralytics transformer encoder, layer, MLP block, LayerNorm2d and the deformable transformer decoder layer. Expand your understanding of these crucial AI modules.
- [utils](https://docs.ultralytics.com/reference/nn/modules/utils): Explore the detailed reference of utility functions in the Ultralytics PyTorch modules. Learn about initialization, inverse sigmoid, and multiscale deformable attention.
- [tasks](https://docs.ultralytics.com/reference/nn/tasks): Dive into the intricacies of YOLO tasks.py. Learn about DetectionModel, PoseModel and more for powerful AI development.
- [text_model](https://docs.ultralytics.com/reference/nn/text_model): Documentation for text encoding models in Ultralytics YOLOE, supporting both OpenAI CLIP and Apple MobileCLIP implementations for vision-language tasks.
- [muon](https://docs.ultralytics.com/reference/optim/muon): Explore Ultralytics Muon optimizer with Newton-Schulz orthogonalization for neural network training. Includes MuSGD hybrid optimizer and momentum-based updates.
- [ai_gym](https://docs.ultralytics.com/reference/solutions/ai_gym): Explore the AI Gym class for real-time pose detection and gym step counting using Ultralytics YOLO. Learn to implement pose estimation effectively.
- [analytics](https://docs.ultralytics.com/reference/solutions/analytics): Explore the Analytics class in Ultralytics for visual analytics. Learn to create and update line, bar, and pie charts efficiently.
- [config](https://docs.ultralytics.com/reference/solutions/config): Configure and customize Ultralytics Vision AI solutions using the SolutionConfig class. Define model paths, regions of interest, visualization options, tracking parameters, and keypoint analytics with a clean, type-safe dataclass structure for scalable development.
- [distance_calculation](https://docs.ultralytics.com/reference/solutions/distance_calculation): Explore the Ultralytics distance calculation module. Learn to calculate distances between objects in real-time video streams with our comprehensive guide.
- [heatmap](https://docs.ultralytics.com/reference/solutions/heatmap): Learn how to use the Ultralytics Heatmap module for real-time video analysis with object tracking and heatmap generation.
- [instance_segmentation](https://docs.ultralytics.com/reference/solutions/instance_segmentation): This page provides a detailed reference for the InstanceSegmentation class in the Ultralytics solutions package, enabling instance segmentation in images and videos.
- [object_blurrer](https://docs.ultralytics.com/reference/solutions/object_blurrer): This page provides a detailed reference for the ObjectBlurrer class in the Ultralytics solutions package, which enables real-time blurring of detected objects in images and videos.
- [object_counter](https://docs.ultralytics.com/reference/solutions/object_counter): Explore the Ultralytics Object Counter for real-time video streams. Learn about initializing parameters, tracking objects, and more.
- [object_cropper](https://docs.ultralytics.com/reference/solutions/object_cropper): Detailed documentation for the ObjectCropper class, part of the Ultralytics solutions package, enabling real-time cropping of detected objects from images and video streams.
- [parking_management](https://docs.ultralytics.com/reference/solutions/parking_management): Explore Ultralytics' Parking Management solution leveraging YOLO for efficient parking zone monitoring and management.
- [queue_management](https://docs.ultralytics.com/reference/solutions/queue_management): Discover the Ultralytics Queue Management script for real-time object tracking and queue management.
- [region_counter](https://docs.ultralytics.com/reference/solutions/region_counter): Explore the Ultralytics Region Counter for real-time video streams. Learn to define regions, track objects, and count activity per zone.
- [security_alarm](https://docs.ultralytics.com/reference/solutions/security_alarm): Discover how Ultralytics' Security Alarm System enhances real-time surveillance with intelligent object detection and tracking. Learn about setup, monitoring, and threat detection.
- [similarity_search](https://docs.ultralytics.com/reference/solutions/similarity_search): Explore the Ultralytics semantic image search solution. Learn how to retrieve images using natural language with CLIP and a simple web app powered by Flask.
- [solutions](https://docs.ultralytics.com/reference/solutions/solutions): Explore the Ultralytics Solution Base class for real-time object counting,virtual gym, heatmaps, speed estimation using Ultralytics YOLO. Learn to implement Ultralytics solutions effectively.
- [speed_estimation](https://docs.ultralytics.com/reference/solutions/speed_estimation): Explore the Ultralytics YOLO-based speed estimation script for real-time object tracking and speed measurement, optimized for accuracy and performance.
- [streamlit_inference](https://docs.ultralytics.com/reference/solutions/streamlit_inference): Explore the live inference capabilities of Streamlit combined with Ultralytics YOLOv8. Learn to implement real-time object detection in your web applications with our comprehensive guide.
- [trackzone](https://docs.ultralytics.com/reference/solutions/trackzone): Discover Ultralytics' TrackZone solution for real-time object tracking within defined zones. Gain insights into initializing regions, tracking objects exclusively within specific areas, and optimizing video stream processing for region-based object detection.
- [vision_eye](https://docs.ultralytics.com/reference/solutions/vision_eye): Discover the Ultralytics VisionEye solution for object tracking and analysis. Learn how to initialize parameters, map vision points, and track objects in real-time.
- [basetrack](https://docs.ultralytics.com/reference/trackers/basetrack): Discover the BaseTrack classes and methods for object tracking in YOLO by Ultralytics. Learn about TrackState, BaseTrack attributes, and methods.
- [bot_sort](https://docs.ultralytics.com/reference/trackers/bot_sort): Explore the robust object tracking capabilities of the BOTrack and BOTSORT classes in the Ultralytics Bot SORT tracker API. Enhance your YOLO26 projects.
- [byte_tracker](https://docs.ultralytics.com/reference/trackers/byte_tracker): Explore the BYTETracker module in Ultralytics for state-of-the-art object tracking using Kalman filtering. Learn about its classes, methods, and attributes.
- [deep_oc_sort](https://docs.ultralytics.com/reference/trackers/deep_oc_sort): Explore the Deep OC-SORT module in Ultralytics for observation-centric multi-object tracking with ReID appearance features and camera motion compensation. Learn about its classes, methods, and attributes.
- [fast_tracker](https://docs.ultralytics.com/reference/trackers/fast_tracker): Explore the FastTracker module in Ultralytics for occlusion-aware multi-object tracking with Kalman rollback and init-IoU suppression. Learn about its classes, methods, and attributes.
- [oc_sort](https://docs.ultralytics.com/reference/trackers/oc_sort): Explore the OC-SORT module in Ultralytics for observation-centric multi-object tracking with Kalman filtering. Learn about its classes, methods, and attributes.
- [track](https://docs.ultralytics.com/reference/trackers/track): Explore the track.py script for Ultralytics object tracking. Learn how on_predict_start, on_predict_postprocess_end, and register_tracker functions work.
- [track_tracker](https://docs.ultralytics.com/reference/trackers/track_tracker): Explore the TrackTrack module in Ultralytics for multi-cue online multi-object tracking with HMIoU, iterative assignment, and track-aware initialization. Learn about its classes, methods, and attributes.
- [gmc](https://docs.ultralytics.com/reference/trackers/utils/gmc): Explore the Generalized Motion Compensation (GMC) class for tracking and object detection with methods like ORB, SIFT, ECC, and more.
- [kalman_filter](https://docs.ultralytics.com/reference/trackers/utils/kalman_filter): Explore Kalman filter implementations like KalmanFilterXYAH and KalmanFilterXYWH for tracking bounding boxes in image space using Ultralytics.
- [matching](https://docs.ultralytics.com/reference/trackers/utils/matching): Explore the utility functions for matching in trackers used by Ultralytics, including linear assignment, IoU distance, embedding distance, and more.
- [reid](https://docs.ultralytics.com/reference/trackers/utils/reid): Reference for the shared ReID encoder and build_encoder utility used by BoT-SORT, Deep OC-SORT, and TrackTrack.
- [stracks](https://docs.ultralytics.com/reference/trackers/utils/stracks): Reference for shared track-pool utilities including merge, joint, subtract, duplicate removal, and global motion compensation helpers.
- [__init__](https://docs.ultralytics.com/reference/utils/__init__): Explore the comprehensive reference for ultralytics.utils in the Ultralytics library. Enhance your ML workflow with these utility functions.
- [autobatch](https://docs.ultralytics.com/reference/utils/autobatch): Discover how to automatically estimate the best YOLO batch size for optimal CUDA memory usage in PyTorch using Ultralytics' autobatch utility.
- [autodevice](https://docs.ultralytics.com/reference/utils/autodevice): Discover how to automatically select the most idle GPU using PyTorch and NVIDIA (nvidia-ml-py) with this AutoDevice script. Ideal for optimizing GPU usage in deep learning and computer vision tasks.
- [benchmarks](https://docs.ultralytics.com/reference/utils/benchmarks): Explore YOLO model benchmarking for speed and accuracy with formats like PyTorch, ONNX, TensorRT, and more. Detailed profiling & usage guides.
- [base](https://docs.ultralytics.com/reference/utils/callbacks/base): Discover the essential base callbacks in Ultralytics for training, validation, prediction, and exporting models efficiently.
- [clearml](https://docs.ultralytics.com/reference/utils/callbacks/clearml): Learn how to integrate ClearML with Ultralytics YOLO using detailed callbacks for pretraining, training, validation, and final logging.
- [comet](https://docs.ultralytics.com/reference/utils/callbacks/comet): Explore the integration of Comet callbacks in Ultralytics YOLO, enabling advanced logging and monitoring for your machine learning experiments.
- [dvc](https://docs.ultralytics.com/reference/utils/callbacks/dvc): Learn to integrate DVCLive with Ultralytics for enhanced logging during training. Step-by-step methods for setting up and optimizing DVC callbacks.
- [hub](https://docs.ultralytics.com/reference/utils/callbacks/hub): Explore detailed guides on Ultralytics callbacks, including pretrain, model save, train start/end, and more. Enhance your ML training workflows with ease.
- [mlflow](https://docs.ultralytics.com/reference/utils/callbacks/mlflow): Learn how to set up and customize MLflow logging for Ultralytics YOLO. Log metrics, parameters, and model artifacts easily.
- [neptune](https://docs.ultralytics.com/reference/utils/callbacks/neptune): Learn how to use NeptuneAI with Ultralytics for advanced logging and tracking of experiments. Detailed setup and callback functions included.
- [platform](https://docs.ultralytics.com/reference/utils/callbacks/platform): Platform callback functions for console logging during YOLO11 training lifecycle events.
- [raytune](https://docs.ultralytics.com/reference/utils/callbacks/raytune): Learn how to integrate Ray Tune with Ultralytics YOLO for efficient hyperparameter tuning and performance tracking.
- [tensorboard](https://docs.ultralytics.com/reference/utils/callbacks/tensorboard): Learn how to integrate and use TensorBoard with Ultralytics for effective model training visualization.
- [wb](https://docs.ultralytics.com/reference/utils/callbacks/wb): Learn how Ultralytics YOLO integrates with WandB using custom callbacks for logging metrics and visualizations.
- [checks](https://docs.ultralytics.com/reference/utils/checks): Explore utility functions for Ultralytics YOLO such as checking versions, image sizes, and requirements.
- [cpu](https://docs.ultralytics.com/reference/utils/cpu): Reference documentation for CPUInfo, a lightweight utility to get system CPU details in Ultralytics.
- [dist](https://docs.ultralytics.com/reference/utils/dist): Explore Ultralytics' utilities for distributed training including DDP file generation, command setup, and cleanup. Improve multi-node training efficiency.
- [downloads](https://docs.ultralytics.com/reference/utils/downloads): Explore and utilize the Ultralytics download utilities to handle URLs, zip/unzip files, and manage GitHub assets effectively.
- [errors](https://docs.ultralytics.com/reference/utils/errors): Explore error handling for Ultralytics YOLO. Learn about custom exceptions like HUBModelError to manage model fetching issues effectively.
- [events](https://docs.ultralytics.com/reference/utils/events): Reference for utilities supporting telemetry, analytics, and event handling with lightweight background requests.
- [axelera](https://docs.ultralytics.com/reference/utils/export/axelera): Axelera export utilities for converting PyTorch models to Axelera format for deployment on Metis AI processors. Supports INT8 quantization and optimized inference for computer vision workloads on Axelera hardware.
- [coreml](https://docs.ultralytics.com/reference/utils/export/coreml): CoreML export utilities for converting PyTorch YOLO models to CoreML format for Apple devices. Supports iOS deployment with FP16/INT8 quantization, NMS pipeline integration, and optimized inference on Apple Silicon and mobile devices.
- [deepx](https://docs.ultralytics.com/reference/utils/export/deepx): Reference for the Ultralytics DEEPX export utility. Learn how to convert ONNX models to DEEPX format using the DX-Compiler.
- [engine](https://docs.ultralytics.com/reference/utils/export/engine): TensorRT engine export utilities for converting ONNX models to optimized TensorRT engines. Provides functions for ONNX export from PyTorch models and TensorRT engine generation with support for FP16/INT8 quantization, dynamic shapes, DLA acceleration, and INT8 calibration for NVIDIA GPU inference optimization.
- [executorch](https://docs.ultralytics.com/reference/utils/export/executorch): Explore the Ultralytics ExecuTorch export utility for converting YOLO models to ExecuTorch (.pte) format for efficient on-device inference on mobile and edge devices.
- [imx](https://docs.ultralytics.com/reference/utils/export/imx): Learn how to export PyTorch models to Sony IMX format using Ultralytics utilities. Comprehensive guide for configurations and precision optimizations.
- [litert](https://docs.ultralytics.com/reference/utils/export/litert): LiteRT export utilities for converting PyTorch YOLO models to LiteRT format using litert_torch. Supports FP16 and INT8 quantization for optimized edge deployment.
- [mnn](https://docs.ultralytics.com/reference/utils/export/mnn): MNN export utilities for converting ONNX models to MNN format for efficient inference on mobile and embedded devices. Supports FP16 and INT8 weight quantization for optimized deployment using Alibaba's MNN framework.
- [ncnn](https://docs.ultralytics.com/reference/utils/export/ncnn): NCNN export utilities for converting PyTorch YOLO models to NCNN format using PNNX. Optimized for mobile and embedded platforms with support for FP16 inference on ARM architectures.
- [onnx](https://docs.ultralytics.com/reference/utils/export/onnx): Reference for the Ultralytics ONNX export utilities. Learn how ONNX INT8 quantization uses ONNX Runtime calibration data readers.
- [openvino](https://docs.ultralytics.com/reference/utils/export/openvino): OpenVINO export utilities for converting PyTorch YOLO models to OpenVINO format with support for FP16 compression and INT8 quantization via NNCF. Provides optimized inference for Intel hardware including CPUs, GPUs, and VPUs.
- [paddle](https://docs.ultralytics.com/reference/utils/export/paddle): PaddlePaddle export utilities for converting PyTorch YOLO models to Paddle format using X2Paddle. Enables deployment on PaddlePaddle inference engine with support for both CPU and GPU backends.
- [qnn](https://docs.ultralytics.com/reference/utils/export/qnn): Reference for the Ultralytics Qualcomm QNN export utility. Learn how to compile ONNX models to the QNN format locally with the ONNX Runtime QNN Execution Provider.
- [rknn](https://docs.ultralytics.com/reference/utils/export/rknn): RKNN export utilities for converting ONNX models to RKNN format for Rockchip NPUs with floating-point and INT8 quantized export support.
- [tensorflow](https://docs.ultralytics.com/reference/utils/export/tensorflow): TensorFlow export utilities for converting PyTorch models to various TensorFlow formats. Provides functions for converting models to TensorFlow SavedModel, Protocol Buffer (.pb), and Edge TPU formats via ONNX intermediate representation with support for INT8 quantization and calibration.
- [torchscript](https://docs.ultralytics.com/reference/utils/export/torchscript): TorchScript export utilities for converting PyTorch YOLO models to TorchScript format with metadata for production deployment and C++ inference.
- [files](https://docs.ultralytics.com/reference/utils/files): Explore the utility functions and context managers in Ultralytics like WorkingDirectory, increment_path, file_size, and more. Enhance your file handling in Python.
- [git](https://docs.ultralytics.com/reference/utils/git): Utilities for retrieving Git repository metadata such as branch, commit, and origin URL, used in Ultralytics projects.
- [instance](https://docs.ultralytics.com/reference/utils/instance): Explore Ultralytics utilities for bounding boxes and instances, providing detailed documentation on handling bbox formats, conversions, and more.
- [logger](https://docs.ultralytics.com/reference/utils/logger): High-performance console output capture with API/file streaming for YOLO11 training logs.
- [loss](https://docs.ultralytics.com/reference/utils/loss): Explore detailed descriptions and implementations of various loss functions used in Ultralytics models, including Varifocal Loss, Focal Loss, Bbox Loss, and more.
- [metrics](https://docs.ultralytics.com/reference/utils/metrics): Explore detailed metrics and utility functions for model validation and performance analysis with Ultralytics' metrics module.
- [nms](https://docs.ultralytics.com/reference/utils/nms): Custom NMS implementation for Ultralytics YOLO with TorchNMS class for torchvision-free inference and fast-nms for oriented bounding boxes. Optimized for speed and accuracy.
- [ops](https://docs.ultralytics.com/reference/utils/ops): Explore detailed documentation on utility operations in Ultralytics including non-max suppression, bounding box transformations, and more.
- [patches](https://docs.ultralytics.com/reference/utils/patches): Explore and contribute to Ultralytics' utils/patches.py. Learn about the imread, imwrite, imshow, and torch_save functions.
- [plotting](https://docs.ultralytics.com/reference/utils/plotting): Explore detailed functionalities of Ultralytics plotting utilities for data visualizations and custom annotations in ML projects.
- [tal](https://docs.ultralytics.com/reference/utils/tal): Explore the TaskAlignedAssigner in Ultralytics YOLO. Learn about the TaskAlignedMetric and its applications in object detection.
- [torch_utils](https://docs.ultralytics.com/reference/utils/torch_utils): Explore valuable torch utilities from Ultralytics for optimized model performance, including device selection, model fusion, and inference optimization.
- [tqdm](https://docs.ultralytics.com/reference/utils/tqdm): Lightweight zero-dependency progress bar for Ultralytics with rich-style displays, GitHub Actions support, and comprehensive formatting options.
- [triton](https://docs.ultralytics.com/reference/utils/triton): Learn how to use the TritonRemoteModel class for interacting with remote Triton Inference Server models. Detailed guide with code examples and attributes.
- [tuner](https://docs.ultralytics.com/reference/utils/tuner): Explore how to use ultralytics.utils.tuner.py for efficient hyperparameter tuning with Ray Tune. Learn implementation details and example usage.
- [uploads](https://docs.ultralytics.com/reference/utils/uploads): Explore the Ultralytics upload utilities with retry logic, progress bars, and signed URL support for cloud storage.

## Help
- [Help](https://docs.ultralytics.com/help): Explore the Ultralytics Help Center with guides, FAQs, CI processes, and policies to support your YOLO model experience and contributions.
- [Frequently Asked Questions (FAQ)](https://docs.ultralytics.com/help/FAQ): Explore common questions and solutions related to Ultralytics YOLO, from hardware requirements to model fine-tuning and real-time detection.
- [Contributing Guide](https://docs.ultralytics.com/help/contributing): Learn how to contribute to Ultralytics YOLO open-source repositories. Follow guidelines for pull requests, code of conduct, and bug reporting.
- [Continuous Integration (CI) Guide](https://docs.ultralytics.com/help/CI): Learn about Ultralytics CI actions, Docker deployment, broken link checks, CodeQL analysis, and PyPI publishing to ensure high-quality code.
- [Contributor License Agreement (CLA)](https://docs.ultralytics.com/help/CLA): Review the terms for contributing to Ultralytics projects. Learn about copyright, patent licenses, and moral rights for your contributions.
- [Minimum Reproducible Example (MRE) Guide](https://docs.ultralytics.com/help/minimum-reproducible-example): Learn how to create effective Minimum Reproducible Examples (MRE) for bug reports in Ultralytics YOLO repositories. Follow our guide for efficient issue resolution.
- [Code of Conduct](https://docs.ultralytics.com/help/code-of-conduct): Join our welcoming community! Learn about the Ultralytics Code of Conduct to ensure a harassment-free experience for all participants.
- [EHS Policy](https://docs.ultralytics.com/help/environmental-health-safety): Explore Ultralytics' commitment to Environmental, Health, and Safety (EHS) policies. Learn about our measures to ensure safety, compliance, and sustainability.
- [Security Policy](https://docs.ultralytics.com/help/security): Learn about the security measures and tools used by Ultralytics to protect user data and systems. Discover how we address vulnerabilities with Snyk, CodeQL, Dependabot, and more.
- [Privacy Policy](https://docs.ultralytics.com/help/privacy): Discover how Ultralytics collects and uses anonymized data to enhance the YOLO Python package while prioritizing user privacy and control.