You Only Look Once (YOLO) is one of the most well-known model architectures to have dominated the computer vision space. Its object detection algorithm is renowned for fast image processing results and improved accuracy. The YOLO algorithm strives to predict an object’s class and the bounding box that pinpoints its location on the input image.

Several iterations of YOLO have been released since Joseph Redmon first introduced it in 2015; the most current was created by AI platform Ultralytics, who also made versions YOLO v3 and YOLO v5. 

About YOLO v8:

YOLO v8 is a state-of-the-art model that is cutting-edge and has new features to improve performance and versatility. It claims to be faster, precise for better object detection, image segmentation and classification. 

Built on PyTorch, both CPU and GPU support it. YOLO v8 scores higher 64% of the time when matched against YOLO v5. All YOLO v8 models are pretrained. Classification models are pretrained on the ImageNet dataset, while detection and segmentation models are pretrained on the COCO dataset.

YOLO v8 can now be used both independently through the terminal and as a part of extensive computer vision applications, thanks to the new YOLOv8 API. The command line interface with YOLO v8 allows you to train, validate, or infer models on various tasks and versions. The CLI doesn’t need any coding or customisation; all tasks are accessible through the terminal. The YOLO v8 SDK has a Python model and trainer interface, so you can use the YOLO model within a customised Python script. This is a new addition, as it could only be done previously by doing a repository fork and altering your own code.

You can install YOLO v8 from the GitHub source or through pip. Check more here.