yolov5
Packaged version of the Yolov5 object detector
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python >=3.7.
- torch and torchvision must be installed; GPU support optional but recommended for inference speed.
- Low install friction with a pure-Python wheel.
License · maintenance · safety
GPL (copyleft) — 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.
last release 2024-11-11 (641 days) · last repo commit 2026-03-20 · 291 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 241,766 downloads/mo, #8,870 on PyPI
Alternatives
Verify before relying
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()- 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.
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 on it.
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
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.
Requires Python >=3.7. torch and torchvision must be installed; GPU support optional but recommended for inference speed.
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()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
| License | GPL copyleft |
| Python support | Supports the current Python release >=3.7 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 23 packagesgitpythonmatplotlibnumpyopencv-pythonPillowpsutilPyYAMLrequestsscipythoptorchtorchvisiontqdmultralyticstensorboardpandasseabornsetuptoolsfireboto3sahihuggingface-hubroboflow |
| Maintenance | Actively maintained 641 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 241,766 / month, #8,870 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersIntended Audience :: Science/ResearchLicense :: OSI Approved :: GNU General Public License (GPL)Operating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.7Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9Topic :: EducationTopic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Scientific/Engineering :: Image RecognitionTopic :: Software Development :: LibrariesTopic :: Software Development :: Libraries :: Python Modules |
Evidence: yolov5-7.0.14-py37.py38.py39.py310-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “object detection yolo”
- yolov5YOLOv5 is a packaged object detection model that runs inference on…
- ultralyticsUltralytics YOLO provides a unified framework for training and…
- pybboxesConverts between bounding box formats (COCO, YOLO, VOC, FiftyOne,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Libraries packages
urllib3 is an HTTP client library that provides thread-safe connection pooling, SSL/TLS verification, multipart file uploads, request retries, compression support, and proxy handling for Python applications.
Requests is a Python HTTP library that simplifies sending HTTP/1.1 requests with automatic handling of headers, authentication, cookies, and response parsing.
Pluggy provides a plugin system that lets you define hook specifications and register implementations to be called in sequence, enabling extensible Python applications without tight coupling.
Install it if you're building an extensible application or framework.
Provides parsing, arithmetic, and recurrence rule computation for dates and times, with timezone support and iCalendar RFC compliance.
Install it if you need to parse flexible date strings, compute relative dates, handle timezones, or work with recurrence rules—it's the de facto choice for these tasks.
Six provides utility functions to write Python code that runs on both Python 2.7 and Python 3.3+, smoothing over language differences between the two versions.
pytest is a testing framework that lets you write test functions using plain assert statements and automatically discovers and runs them, with detailed failure reporting.
See also ultralytics · roboflow · inference-cli · inference-models · boxmot · qrdet · groundingdino-py · norfair · inference-sdk · sahi