You're reading from Hands-On Computer Vision with Detectron2

Product type Book

Published in Apr 2023

Publisher Packt

ISBN-13 9781800561625

Pages 318 pages

Edition 1st Edition

Languages

Python

Concepts

Computer Vision

Author (1):

Van Vung Pham

Table of Contents (20) Chapters

Preface

Part 1: Introduction to Detectron2

Chapter 1: An Introduction to Detectron2 and Computer Vision Tasks

Chapter 2: Developing Computer Vision Applications Using Existing Detectron2 Models

Part 2: Developing Custom Object Detection Models

Chapter 3: Data Preparation for Object Detection Applications

Chapter 4: The Architecture of the Object Detection Model in Detectron2

Chapter 5: Training Custom Object Detection Models

Chapter 6: Inspecting Training Results and Fine-Tuning Detectron2’s Solvers

Chapter 7: Fine-Tuning Object Detection Models

Chapter 8: Image Data Augmentation Techniques

Chapter 9: Applying Train-Time and Test-Time Image Augmentations

Part 3: Developing a Custom Detectron2 Model for Instance Segmentation Tasks

Chapter 10: Training Instance Segmentation Models

Chapter 11: Fine-Tuning Instance Segmentation Models

Part 4: Deploying Detectron2 Models into Production

Chapter 12: Deploying Detectron2 Models into Server Environments

Chapter 13: Deploying Detectron2 Models into Browsers and Mobile Environments

Index

Why subscribe?

Other Books You May Enjoy

Selecting the best model

Selecting the best model requires evaluation metrics. Therefore, we need to understand the common evaluation terminologies and evaluation metrics used for object detection tasks before choosing the best model. Additionally, after having the best model, this section also covers code to sample and visualize a few prediction results to qualitatively evaluate the chosen model.

Evaluation metrics for object detection models

Two main evaluation metrics are used for the object detection task: mAP@0.5 (or AP50) and F1-score (or F1). The former is the mean of average precisions (mAP) at the intersection over the union (IoU) threshold of 0.5 and is used to select the best models. The latter represents the harmonic means of precision and recall and is used to report how the chosen model performs on a specific dataset. The definitions of these two metrics use the computation of Precision and Recall: