Optimized Yolo with Dropout

Abstract

The goal is to recognize different objects by applying the YOLO (You Only Look Once) technique. This technique has a few benefits in contrast to any other techniques for object detection and tracking. In some codes as Fast Convolutional Neural Network (FCNN) and Convolutional Neural Network (CNN) the code will not focus at the picture entirely but for the case of YOLO, the code focuses the entire image by concluding the detection boxes utilizing a convolutional neural framework and the probability of classes for the bounding boxes and finds the image immediately in contrast to some different codes. The dropout layer is also programed at the end to avoid over fitting issues. It is seen that using dropout the results have improved much.