PyTorch Object Detection :: Darknet TXT
YOLOv4 was published in April 2020. YOLOv4 achieved state of the art performance on the COCO dataset for object detection.
YOLOv4 breaks the object detection task into two pieces, regression to identify object positioning via bounding boxes and classification to determine the object's class.
YOLOv4 operates in real time.
By using YOLOv4, you are implementing many of the past research contributions in the YOLO family along with a series of new contributions unique to YOLOv4 including new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, CmBN, DropBlock regularization, and CIoU loss. In short, with YOLOv4, you're using a better object detection network architecture and new data augmentation techniques.