A PyTorch implementation of YOLOv3 for real-time object detection, supporting export to ONNX, CoreML, and TFLite.
Ultralytics YOLOv3 is a PyTorch-based implementation of the YOLOv3 (You Only Look Once) object detection model. It is designed for real-time detection of objects in images and videos, offering improved accuracy and speed over earlier versions. The project solves the problem of efficient and accurate object detection for applications ranging from academic research to commercial deployment.
Computer vision researchers, AI engineers, and developers working on real-time object detection tasks, including those needing to deploy models to edge devices or various frameworks.
Developers choose Ultralytics YOLOv3 for its reliable PyTorch implementation, ease of use, and support for exporting to multiple deployment formats like ONNX, CoreML, and TFLite. Its integration with popular AI platforms and comprehensive training/inference scripts provide a streamlined workflow for vision projects.
YOLOv3 in PyTorch > ONNX > CoreML > TFLite
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.