LibreYOLO/libreyolo

LibreYOLO is a MIT licensed open source computer vision library

What it solves

LibreYOLO provides a unified, MIT-licensed API for a vast array of computer vision tasks. It eliminates the need to switch between different libraries or complex setups when moving between detection, segmentation, pose estimation, and other vision-related AI tasks.

How it works

The library uses a single, consistent interface where the specific task is determined by the model checkpoint loaded. Users can perform inference, training, and exporting across twenty different vision tasks using the same three lines of code. It supports a wide range of sources including images, webcams, RTSP streams, YouTube URLs, and screen captures.

Who it’s for

It is designed for developers and researchers who need a comprehensive computer vision toolkit that is easy to install and deploy across various hardware backends.

Highlights

  • Unified API: One interface for detection, segmentation, pose, depth, OCR, and more.
  • Extensive Model Support: Includes a massive library of models for tasks like YOLOv9, SAM 2, Depth Anything, and various VLMs.
  • Cros-platform Export: Supports twelve different formats including ONNX, TensorRT, OpenVINO, and CoreML.
  • Integrated Training: Built-in support for multi-GPU training, LoRA, and integration with logging tools like Weights & Biases and MLflow.
  • Flexible Input: Handles diverse input sources such as live streams and screen captures.

Related

  • Project
    Geekgineer/YOLOs-CPP

    A production-ready C++ inference engine that provides a unified API for the entire YOLO family, supporting tasks from object detection to metric depth estimation.

  • Project
    ultralytics/ultralytics

    A comprehensive computer vision framework featuring YOLO models for real-time object detection, segmentation, classification, and pose estimation.

  • Project
    Koldim2001/YOLO-Patch-Based-Inference

    A Python library that enables patch-based inference for YOLO models to improve the detection of small objects in large images through image tiling and result consolidation.

  • Project
    roboflow/roboflow-python

    Roboflow‑python is the official Python client for the Roboflow computer‑vision platform. It lets you programmatically create workspaces/projects, upload and version datasets, trigger model training, and run inference on hosted or self‑hosted models. Install via `pip install roboflow` (or the lightweight `roboflow-slim`), authenticate with an API key or login, and use a simple object hierarchy (workspace → project → version) to manage the full CV lifecycle.

  • Project
    ultralytics/yolov5

    YOLOv5 is a PyTorch‑based, open‑source object detection/segmentation/classification model suite from Ultralytics, offering multiple model sizes, simple Python/CLI inference, one‑line training, and export to many deployment formats.