PyTorch Computer Vision Cookbook by Michael Avendi

PyTorch Computer Vision Cookbook by Michael Avendi

Author:Michael Avendi [Michael Avendi]
Language: eng
Format: epub, mobi
Tags: COM016000 - COMPUTERS / Computer Vision and Pattern Recognition, COM004000 - COMPUTERS / Intelligence (AI) and Semantics, COM044000 - COMPUTERS / Neural Networks
Publisher: Packt
Published: 2020-03-20T12:30:58+00:00


Multi-Object Detection

Object detection is the process of locating and classifying existing objects in an image. Identified objects are shown with bounding boxes in the image. There are two methods for general object detection: region proposal-based and regression/classification-based. In this chapter, we will use a regression/classification-based method called YOLO.

YOLO, which stands for You Only Look Once, is based on a series of papers that can be accessed from a variety of links (You Only Look Once: Unified, Real-Time Object Detection (https://arxiv.org/abs/1506.02640), YOLO9000: Better, Faster, Stronger (https://arxiv.org/abs/1612.08242), and YOLOv3: An Incremental Improvement (https://arxiv.org/abs/1804.02767)). YOLO-v3 is the latest version of the series and performs better in terms of accuracy than previous versions. Thus, we will focus on developing Yolo-v3 using PyTorch in this chapter.

In this chapter, we will learn how to implement the YOLO-v3 algorithm and train and deploy it for object detection using PyTorch.

In particular, we will cover the following recipes:

Creating datasets

Creating a YOLO-v3 model

Defining the loss function

Training the model

Deploying the model



Download



Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.