# YOLOv5

YOLOv5 is a fast, accurate object-detection model that identifies items in photos and video feeds in real time for surveillance, automation, and computer vision projects. It is open source and self-hosted, installable on Docker Hub.

Canonical page: https://ourlocalhost.com/app/6018/yolov5

## Description

YOLOv5 is a fast, accurate object-detection model that identifies items in photos and video feeds in real time for surveillance, automation, and computer vision projects.

## Platform availability

Available on 0 of 10 platforms.

## Health score

77/100 (Good), based on 4 of 5 factors.
- Maintained: 100 (last commit 5 days ago)
- Popular: 95 (58,290 GitHub stars)
- Easy to install: 25 (0 install platforms, install notes, Docker image)
- Security check: 61 (no serious findings, 5 minor, CI, tests, OpenSSF Scorecard 5.4/10)

## Links

- GitHub: https://github.com/ultralytics/yolov5
- Docker Hub: https://hub.docker.com/r/ultralytics/yolov5
- Official website: https://docs.ultralytics.com/yolov5/
- Documentation: https://docs.ultralytics.com/

## Common questions

### How do I run YOLOv5 in Docker with GPU support?

Install the Nvidia drivers and the NVIDIA Container Toolkit first. Then run the YOLOv5 container with --ipc=host --gpus all so it can use the GPU.

### Can I train YOLOv5 on a custom dataset?

Yes, the YOLOv5 documentation includes a tutorial for training the model on custom data.

### How can I load a pretrained YOLOv5 model?

You can load pretrained models through PyTorch Hub.

### Can I export YOLOv5 for deployment?

The documentation covers exporting to TFLite, ONNX, CoreML, and TensorRT.

### How do I request an enterprise license for YOLOv5?

You can request an Enterprise License through Ultralytics Licensing.

---
Source: Our Local Host (https://ourlocalhost.com/app/6018/yolov5), the self-hosted and open-source app directory.
