# ultralytics/yolov5

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

Repository: https://github.com/ultralytics/yolov5
Canonical: https://ross.abutalabs.com/products/yolov5
Homepage: https://docs.ultralytics.com/yolov5/
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: yolov5, object-detection, pytorch, onnx, coreml, tflite, yolo, deep-learning, ultralytics, computer-vision, image-classification, inference, instance-segmentation, model-export, model-training, tensorrt
Last push: 2026-08-24T08:38:22+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 8, longevity 100
- inputs: {"age_days": 2298, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 57929, forks 17475 (observed 2026-08-28T04:12:18.584765+00:00)

## What it is
Ultralytics YOLOv5 is a PyTorch-based computer vision model family for real-time object detection, instance segmentation, and image classification, with training and export to formats like ONNX, CoreML, TFLite, and TensorRT. It is now labeled a legacy model, with Ultralytics recommending newer successors such as YOLOv8, YOLO11, and YOLO26 for new projects.

## Use cases
- detect objects in images and video in real time
- train a custom object detection model on my own dataset
- run instance segmentation on images
- classify images with a pretrained model
- export a model to ONNX or TensorRT for edge deployment
- run inference via PyTorch Hub with a few lines of code
- deploy a detection model on cloud GPUs like AWS or GCP

## When to choose
- you need a battle-tested, widely documented real-time object detection model
- you want easy training on custom datasets with extensive tutorials
- you need multi-format export (ONNX, CoreML, TFLite, TensorRT) for deployment
- you are maintaining an existing YOLOv5-based pipeline

## When to avoid
- you are starting a new project and want the latest accuracy and features - prefer YOLOv8, YOLO11, or YOLO26
- you need a permissively licensed model for closed-source commercial products - YOLOv5 is AGPL-3.0 and requires an enterprise license
- you need tasks beyond detection, segmentation, and classification such as pose estimation or tracking

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: yolo, object-detection, instance-segmentation, image-classification, pytorch, onnx, tensorrt, model-export, model-training, inference, real-time, gpu, docker

## Member repositories
- ultralytics/yolov5 (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:18.584765+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:18:20.382775+00:00, confidence not recorded.
  - readme: https://github.com/ultralytics/yolov5 (fetched 2026-08-28T04:12:18.584765+00:00, sha e5a2eb57dbf8)
  - homepage: https://docs.ultralytics.com/yolov5/ (fetched 2026-08-28T18:02:10.222099+00:00, sha 5801dc8a198f)
  - site_page: https://docs.ultralytics.com/quickstart (fetched 2026-08-28T18:02:10.224207+00:00, sha 80d7989c34f3)
  - site_page: https://docs.ultralytics.com/yolov5/quickstart-tutorial (fetched 2026-08-28T18:02:10.226292+00:00, sha ebf4e4a49f02)
  - site_page: https://docs.ultralytics.com/integrations (fetched 2026-08-28T18:02:10.228067+00:00, sha 1dec60b917d0)
  - site_page: https://docs.ultralytics.com/ (fetched 2026-08-28T18:02:10.230196+00:00, sha fba5847c3417)
  - site_page: https://docs.ultralytics.com/yolov5/environments/google-cloud-quickstart-tutorial (fetched 2026-08-28T18:02:10.232033+00:00, sha 8b0428f5bac8)
  - site_page: https://docs.ultralytics.com/yolov5/environments/aws-quickstart-tutorial (fetched 2026-08-28T18:02:10.233706+00:00, sha 2d9d1af1db07)
  - site_page: https://docs.ultralytics.com/yolov5/environments/azureml-quickstart-tutorial (fetched 2026-08-28T18:02:10.235438+00:00, sha 37bce7d9a4f4)
  - site_page: https://docs.ultralytics.com/yolov5/environments/docker-image-quickstart-tutorial (fetched 2026-08-28T18:02:10.237129+00:00, sha b20ef4e84ca2)
- Data as of 2026-08-30T08:39:29.467469+00:00.