What it is
A Python library and command-line tool for training, validating, and deploying YOLO models for object detection, instance and semantic segmentation, classification, pose estimation, oriented boxes, and depth estimation. It also tracks detected objects across video frames and exports models to formats for edge and server deployment. Pretrained weights for several YOLO generations are included. Machine learning engineers and researchers use it to build custom vision models on their own datasets with a few lines of code.