Yolov3 is an object detection network part of yolo family (Yolov1, Yolov2). It can detect various things of different sizes, runs quite fast and make real-time inference possible on various devices. It takes images as input, pass it through neural network and get a vector of bounding boxes and class predictions as output. In this project we performed face mask detection using pre trained YOLO v3 model on face dataset. We created a face mask dataset and trained it on our YOLOv3 model. You can refer to the face mask dataset here https://drive.google.com/file/d/1ovGQLmKPgMI6vv8Axq7551jYZEDCw0-G/view?usp=sharing.
The trained yolo v3 cfg file can be refered here https://drive.google.com/file/d/14NuYROBe9WQrifLE15yfduG97GYe0enq/view?usp=sharing.