yolov5

What it is and what it does

YOLOv5 is a packaged wrapper around the Ultralytics YOLOv5 object detector, providing pip-installable access to a production-grade real-time detection model. It detects and localizes objects in images, video streams, and webcam feeds, returning bounding boxes, confidence scores, and class predictions. The package includes training and fine-tuning workflows for custom datasets, model export to multiple formats (ONNX, TorchScript, CoreML, TensorFlow Lite), and a CLI for common tasks.

The package depends on PyTorch, OpenCV, NumPy, and a suite of data-handling and visualization libraries. It integrates with Hugging Face Hub for model sharing, Roboflow for dataset management, and AWS S3 for artifact storage. Training supports COCO-format datasets and Neptune.AI logging. The primary use case is building and deploying object detection pipelines without managing the underlying YOLOv5 repository directly.

Use it for:

• Run inference on images or video to detect and locate objects in real time.
• Fine-tune a pre-trained YOLOv5 model on a custom dataset for domain-specific detection tasks.
• Export a trained model to ONNX, TorchScript, or TensorFlow Lite for deployment on edge devices.
• Stream detections from a webcam or RTSP/RTMP source and save annotated results.
• Integrate object detection into a larger ML pipeline via Python API or CLI commands.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

YOLOv5 is a packaged object detection model that runs inference on images and video to identify and localize objects, with integrated training, validation, export, and CLI support.

Yes, with conditions. YOLOv5 is actively maintained, production-stable, and has no known vulnerabilities. Install friction is low, but the 23 runtime dependencies—especially torch and torchvision—are heavy; ensure your environment can accommodate them and that GPU support is available if you need inference speed. GPL copyleft licensing requires compliance in derivative works. Suitable for research, prototyping, and applications where GPL terms are acceptable.

Install

yolov5 on PyPI

pip install yolov5

uv add yolov5

poetry add yolov5

Installing yolov5

Before you install

Low install friction with a pure-Python wheel. Active maintenance as of 2026-03-20. However, 23 runtime dependencies including torch, torchvision, and opencv-python are heavy; actual installation time and disk footprint will depend on whether these are already present.

License in practice

Licensed under GPL (copyleft). Derivative works and modifications must be distributed under the same license terms; proprietary applications using this package must comply with GPL obligations or obtain an alternative license.

Quickstart

pip install yolov5

import yolov5
model = yolov5.load('yolov5s.pt')
results = model('https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg')
results.show()

Requires Python >=3.7. torch and torchvision must be installed; GPU support optional but recommended for inference speed.

Verify before relying

• Whether pre-trained model weights are downloaded on first load or must be manually staged.
• Memory and compute requirements for different model sizes (yolov5s, yolov5m, yolov5l, yolov5x).
• Performance on edge devices or CPU-only environments.

Package facts

Evidence: yolov5-7.0.14-py37.py38.py39.py310-none-any.whl

Keywords: machine-learning, deep-learning, ml, pytorch, YOLO, object-detection, vision, YOLOv5, YOLOv7

Tags

More Libraries packages