Home › Vision Models › YOLOv5

YOLOv5 - AI Vision Models Tool

Overview

YOLOv5 is a widely used open-source computer vision library for object detection, segmentation, and classification built on PyTorch. It provides a family of pretrained models (yolov5s/yolov5m/yolov5l/yolov5x) optimized for different speed/accuracy trade-offs, and includes end-to-end training, evaluation, and inference scripts. The project emphasizes practical deployment: models can be exported to ONNX, TensorFlow/TFLite, and CoreML formats for edge or mobile runtimes, and supports CPU and GPU inference pipelines for real-time applications. According to the GitHub repository, YOLOv5 is actively maintained (last commit listed on 2025-12-21) and has a large community, with 56,588 stars, 17,392 forks, and 333 contributors. The repo is licensed under AGPL-3.0 and contains extensive documentation, example notebooks, and ready-to-run demos, making it suitable for both research experiments and production prototypes in domains such as autonomous vehicles, retail analytics, robotics, and video surveillance.

GitHub Statistics

  • Stars: 56,588
  • Forks: 17,392
  • Contributors: 333
  • License: AGPL-3.0
  • Primary Language: Python
  • Last Updated: 2025-12-21T17:08:10Z
  • Latest Release: v7.0

The YOLOv5 repository shows strong community engagement and active maintenance: 56,588 stars, 17,392 forks, and 333 contributors (according to the GitHub repository). Frequent commits and a recent commit date (2025-12-21) indicate ongoing development. A large contributor base and many forks suggest numerous community forks, integrations, and third-party resources. The AGPL-3.0 license requires copyleft compliance for distributed derivatives, which teams should consider for commercial deployments.

Installation

Install via pip:

git clone https://github.com/ultralytics/yolov5.git
cd yolov5
pip install -r requirements.txt
python detect.py --weights yolov5s.pt --source data/images
pip install -U git+https://github.com/ultralytics/yolov5  # optional direct pip install

Key Features

  • Pretrained model family (yolov5s/m/l/x) for different speed/accuracy trade-offs
  • Export models to ONNX, CoreML, TFLite, and TensorFlow SavedModel formats
  • Built-in training pipeline with mosaic, mixup, and multi-scale augmentation
  • Segmentation and classification scripts alongside object detection
  • Automatic anchor-clustering and hyperparameter evolution tools
  • Real-time inference optimizations for CPU and CUDA GPU environments
  • Evaluation utilities (mAP, confusion matrix) and compatibility with COCO format

Community

YOLOv5 has a large, active community: 56,588 GitHub stars, 17,392 forks, and 333 contributors. The project receives frequent commits and community contributions, with many community tutorials, notebooks, and third‑party integrations. Issues, pull requests, and forks provide practical examples and deployment recipes, making it easy to find community support and deployment guides.

Last Refreshed: 2026-01-09

Key Information

  • Category: Vision Models
  • Type: AI Vision Models Tool
Visit Official Website

Related Tools

Janus-1.3B

A unified multimodal AI model that decouples visual encoding to support both understanding and generation tasks.
YOLOv10

YOLOv10 is a real-time end-to-end object detection tool that improves upon previous YOLO versions through NMS-free training and a comprehensive architectural design to enhance efficiency and accuracy. It offers state-of-the-art performance across various model sizes and is implemented in PyTorch.
BLIP-2

BLIP-2 is an advanced visual-language model that allows zero-shot image-to-text generation, enabling tasks such as image captioning and visual question answering using a combination of pretrained vision and language models.
DeepSeek-VL2

A series of advanced vision-language models designed for multimodal understanding, available in multiple sizes to suit varying complexity and performance requirements.
JanusFlow-1.3B

JanusFlow-1.3B is a unified multimodal model by DeepSeek that integrates autoregressive language models with rectified flow, enabling both multimodal understanding and image generation.
Ultralytics YOLOv8

A state‐of‐the‐art object detection model by Ultralytics that provides robust capabilities for object detection, instance segmentation, and pose estimation. It offers both CLI and Python integrations with extensive documentation and performance metrics.