References

  1. Redmon, Joseph, and Ali Farhadi. “Yolov3: An incremental improvement.” arXiv preprint arXiv:1804.02767 (2018).
  2. YOLO v2 – Object Detection
  3. YOLO : You Only Look Once – Real Time Object Detection


YOLOv3 From Scratch Using PyTorch

This article discusses about YOLO (v3), and how it differs from the original YOLO and also covers the implementation of the YOLO (v3) object detector in Python using the PyTorch library.

Object detection is a fundamental task in computer vision that is a combination of identifying objects within an image and localizing them by drawing a bounding box around them. It takes an image as input and produces one or more bounding boxes with the class label attached to each bounding box. A lot of research has been done in this domain and various algorithms like YOLO, R-CNN, Fast R-CNN, and Faster R-CNN have been proposed. In this article, we will discuss the YOLO (v3) algorithm.

Similar Reads

YOLO (You Only Look Once)

YOLO (You Only Look Once) are proposed by J. Redmon and A. Farhadi in 2015 to deal with the problems of slow processing speed and complex architectures of state-of-the-art models at that time. In terms of speed, YOLO is one of the best models for object recognition, able to recognize objects and process frames at a rate of up to 150 FPS for small networks. However, In terms of the accuracy of mAP, YOLO was not the state-of-the-art model but has a fairly good Mean Average Precision (mAP) of 63% when trained on PASCAL VOC 2007 and PASCAL VOC 2012. However, Fast R-CNN which was the state of the art at that time has an mAP of 71%....

Implementation of YOLO (v3) Object Detector

Now in this section we will look into implementation of YOLO (v3) object detector in PyTorch. We will first discuss about the dataset we can use to train the model. Then we will discuss about its architecture design, its components and there implementation. Later we will discuss about training the network and test it with a random image....

References

...

Contact Us