# ultralytics/ultralytics

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/ultralytics-ultralytics).**

58,468 stars · 11,196 forks · Python · AGPL-3.0

## Links

- GitHub: https://github.com/ultralytics/ultralytics
- Homepage: https://docs.ultralytics.com
- awesome-repositories: https://awesome-repositories.com/repository/ultralytics-ultralytics.md

## Topics

`cli` `computer-vision` `deep-learning` `hub` `image-classification` `instance-segmentation` `machine-learning` `object-detection` `pose-estimation` `python` `pytorch` `rotated-object-detection` `segment-anything` `tracking` `ultralytics` `yolo` `yolo-world` `yolo11` `yolo26` `yolov8`

## Description

Ultralytics is a comprehensive computer vision framework designed for training, validating, and deploying deep learning models across a wide range of visual recognition tasks. It provides a unified interface for core operations including object detection, instance segmentation, pose estimation, and image classification. By utilizing a modular architecture, the platform allows users to swap model components to balance inference speed and accuracy requirements for diverse applications.

The framework distinguishes itself through its support for real-time processing and flexible deployment. It includes a streaming inference engine that manages memory usage for large-scale video analysis and a format-agnostic export pipeline that translates trained weights into standardized formats for edge and cloud environments. Beyond standard detection, it supports open-vocabulary segmentation, allowing users to identify objects using text or visual prompts, and provides robust multi-object tracking capabilities to maintain identity persistence across video frames.

The platform covers the entire machine learning lifecycle, from dataset retrieval and dynamic data loading to performance benchmarking and experiment tracking. It includes specialized tools for annotating visual results and accessing structured output data, facilitating integration into automated inspection and monitoring workflows. Users can configure training hyperparameters, resume interrupted sessions, and profile model performance to ensure optimal deployment on hardware ranging from mobile devices to high-performance GPUs.

## Tags

### Artificial Intelligence & ML

- [Computer Vision](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/computer-vision.md) — Enables end-to-end development of visual recognition systems, from initial training to production-ready deployment.
- [Model Training and Inference Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-management/model-training-and-inference-engines.md) — Consolidates the entire lifecycle of training, validating, and executing deep learning models into a single, cohesive workflow. ([source](https://docs.ultralytics.com/models/yolov6))
- [Pose Estimation Models](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/language-model-integrations/computer-vision-models/pose-estimation-models.md) — Locates and monitors specific anatomical or object keypoints within video frames and static images. ([source](https://docs.ultralytics.com/tasks/pose))
- [Instance Segmentation Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-libraries/instance-segmentation-engines.md) — Isolates individual object instances in complex scenes through detailed pixel-level segmentation.
- [Computer Vision Training Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/development-orchestration-tools/computer-vision-training-frameworks.md) — Streamlines the process of building and fine-tuning neural networks for complex tasks like segmentation and detection.
- [Object Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-detection-tracking/object-detection.md) — Detects and classifies objects within visual media by generating precise bounding boxes. ([source](https://docs.ultralytics.com/tasks))
- [Object Pose Estimations](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-pose-estimations.md) — Analyzes spatial orientation and movement by tracking keypoint coordinates across video sequences. ([source](https://docs.ultralytics.com/tasks))
- [Image Segmentation](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/image-segmentation.md) — Partitions images into distinct regions by generating high-precision pixel-level masks. ([source](https://docs.ultralytics.com/tasks))
- [Segmentation Model Training](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/image-segmentation/segmentation-model-training.md) — Automates the preparation of custom datasets and the execution of training routines for segmentation models. ([source](https://docs.ultralytics.com/tasks/segment))
- [Pose Estimation Platforms](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/computer-vision/computer-vision-platforms/pose-estimation-platforms.md) — Maintains an integrated environment for tracking human joints and keypoints to derive movement patterns.
- [Model Definition](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/model-definition.md) — Standardizes the structural definition and adaptation of neural network topologies for diverse visual tasks.
- [Edge AI Model Deployment](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/local-and-on-device-inference/edge-ai-model-deployment.md) — Optimizes model weights and architectures for efficient inference on low-power embedded hardware.
- [Inference Result Processors](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-inference-serving/model-integration-pipelines/model-inference/inference-result-processors.md) — Parses and structures raw model outputs into usable formats like bounding boxes, masks, and keypoint coordinates. ([source](https://docs.ultralytics.com/modes/predict))
- [Model Deployment Toolkits](https://awesome-repositories.com/f/artificial-intelligence-ml/model-optimization/inference-deployment/model-deployment-toolkits.md) — Exports and optimizes models for high-performance execution across cloud and edge hardware environments.
- [Object Tracking Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-detection-tracking/object-tracking-systems.md) — Maintains persistent identity across continuous video feeds for multiple detected objects.
- [Neural Network Components](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/architectures/neural-network-components.md) — Organizes neural networks into modular backbone, neck, and head components for easier customization.
- [Inference Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-inference-serving/inference-engines.md) — Executes pre-trained models on various data streams using highly optimized runtime environments. ([source](https://docs.ultralytics.com/modes/predict))
- [Image Classification Models](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/image-classification-models.md) — Assigns descriptive labels to entire images to assist with content moderation and automated cataloging. ([source](https://docs.ultralytics.com/tasks))
- [Object Detection and Tracking](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-detection-tracking.md) — Identifies, localizes, and maintains object trajectories across video frames by assigning unique identifiers to detected entities. ([source](https://docs.ultralytics.com/modes/track))
- [Edge Object Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-detection-tracking/edge-object-detection.md) — Deploys real-time detection models specifically tuned for low-power hardware and edge computing environments. ([source](https://docs.ultralytics.com/models/yolo26))
- [Remote Model Training Services](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/machine-learning-training/distributed-and-accelerated-compute/remote-model-training-services.md) — Coordinates training tasks on remote hardware while providing centralized dashboards for monitoring experimental results. ([source](https://docs.ultralytics.com/platform))
- [Model Export Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/serialization-and-export-formats/model-export-pipelines.md) — Transforms trained neural network weights into multiple standardized formats to ensure cross-platform compatibility.
- [Detection Model Validation](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-evaluation-analysis/machine-learning-evaluation/detection-model-validation.md) — Calculates mean average precision and other performance metrics to verify the accuracy of object detection results. ([source](https://docs.ultralytics.com/tasks/detect))
- [Pose Estimation Validation](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-evaluation-and-validation/pose-estimation-validation.md) — Verifies the precision and recall of human pose detection models by running automated benchmarks against ground truth datasets. ([source](https://docs.ultralytics.com/tasks/pose))
- [Segmentation Model Validation](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-evaluation-and-validation/segmentation-model-validation.md) — Validates segmentation accuracy by calculating performance metrics such as mean average precision for masks and boxes. ([source](https://docs.ultralytics.com/tasks/segment))
- [Training Hyperparameters](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/training-hyperparameters.md) — Manages critical learning configurations like batch size and learning rate to refine model training performance. ([source](https://docs.ultralytics.com/modes/train))
- [Experiment Tracking](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/training-monitoring-and-profiling/training-observability-systems/experiment-tracking.md) — Integrates with external visualization platforms to track training progress and performance metrics in real time. ([source](https://docs.ultralytics.com/modes/train))
- [Streaming Inference Processors](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-inference-serving/inference-engines/streaming-inference-processors.md) — Utilizes memory-efficient generators to maintain high throughput during large-scale video and image stream processing.
- [Computer Vision Segmentation Models](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/architectures/computer-vision-segmentation-models.md) — Isolates pixel-level instances of concepts within images or video using text prompts or image exemplars. ([source](https://docs.ultralytics.com/models/sam-3))
- [Visual Annotation Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/computer-vision/computer-vision-tools/visual-annotation-tools.md) — Applies visual overlays, regions, and labels to images or video frames using specialized plotting utilities. ([source](https://docs.ultralytics.com/solutions))
- [Dataset Management Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/dataset-management/dataset-management-tools.md) — Facilitates the organization of training data and the conversion of models into standard file formats for broad compatibility. ([source](https://docs.ultralytics.com/integrations))
- [Model Exporters](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/serialization-and-export-formats/model-exporters.md) — Converts external object detection models into standardized formats for consistent deployment and inference workflows. ([source](https://docs.ultralytics.com/models/yolov7))
- [Model Evaluation and Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-evaluation-analysis.md) — Benchmarks inference speed, accuracy, and parameter efficiency to visualize performance trade-offs across various hardware constraints. ([source](https://docs.ultralytics.com/compare))
- [Tracking Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/object-tracking/tracking-configurations.md) — Adjusts confidence thresholds and matching logic through configuration files to define specific tracking behaviors. ([source](https://docs.ultralytics.com/modes/track))
- [Model Inference and Serving](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-inference-serving.md) — Controls inference behavior by adjusting parameters such as image sizing, padding strategies, and confidence thresholds. ([source](https://docs.ultralytics.com/modes/predict))
- [Performance Profilers](https://awesome-repositories.com/f/artificial-intelligence-ml/model-optimization/profiling-and-benchmarking/performance-profilers.md) — Measures execution speed, memory usage, and accuracy across different export formats to determine the best configuration for target environments. ([source](https://docs.ultralytics.com/modes))

### Part of an Awesome List

- [Computer Vision](https://awesome-repositories.com/f/awesome-lists/ai/computer-vision.md) — Real-time object detection and tracking for edge devices.
- [Machine Learning](https://awesome-repositories.com/f/awesome-lists/ai/machine-learning.md) — Computer vision models including YOLOv8.
- [Machine Learning Libraries](https://awesome-repositories.com/f/awesome-lists/ai/machine-learning-libraries.md) — Object detection and computer vision framework.

### Data & Databases

- [Dynamic Data Loaders](https://awesome-repositories.com/f/data-databases/data-processing-pipelines/processing-pipelines/dynamic-data-loaders.md) — Adapts various dataset structures and annotation formats on-the-fly to feed training pipelines without requiring manual pre-conversion.
- [Classification Datasets](https://awesome-repositories.com/f/data-databases/data-collections-datasets/classification-datasets.md) — Retrieves diverse classification datasets, ranging from standard benchmarks to large-scale image collections, for training categorization models. ([source](https://docs.ultralytics.com/datasets))

### DevOps & Infrastructure

- [Edge Deployment Tools](https://awesome-repositories.com/f/devops-infrastructure/deployment-management/deployment-strategies/edge-deployment-tools.md) — Applies hardware acceleration and optimization techniques to distribute models to edge devices and web interfaces. ([source](https://docs.ultralytics.com/integrations))

### Programming Languages & Runtimes

- [Inference Result Objects](https://awesome-repositories.com/f/programming-languages-runtimes/programming-utilities/data-structure-type-helpers/data-structures/inference-result-objects.md) — Encapsulates bounding boxes, masks, and keypoints into accessible objects to simplify programmatic interaction with model outputs.