YOLO (You Only Look Once) is an open source neural network framework written in C and CUDA that uses Convolutional Neural Networks for real-time object detection and recognition.
It is fast, easy to install, and supports CPU and GPU computation.
YOLOv7, YOLOv4, and Scaled-YOLOv4 are some of the state-of-the-art object detectors that can be implemented using YOLO.