Hands-on computer vision with Detectron2 : develop object detection and segmentation models with a code and visualization approach / Van Vung Pham, Tommy Dang.

Format:

Book

Author/Creator:

Pham, Van Vung, author.

Dang, Tommy, author.

Language:

English

Subjects (All):

Computer vision.

Physical Description:

1 online resource (318 pages)

Edition:

1st ed.

Place of Publication:

Birmingham, England ; Mumbai : Packt, [2023]

Biography/History:

Pham Van Vung: Van Vung Pham is a passionate research scientist in machine learning, deep learning, data science, and data visualization. He has years of experience and numerous publications in these areas. He is currently working on projects that use deep learning to predict road damage from pictures or videos taken from roads. One of the projects uses Detectron2 and Faster R-CNN to predict and classify road damage and achieve state-of-the-art results for this task. Dr. Pham obtained his PhD from the Computer Science Department, at Texas Tech University, Lubbock, Texas, USA. He is currently an assistant professor at the Computer Science Department, Sam Houston State University, Huntsville, Texas, USA.

Summary:

Computer vision is a crucial component of many modern businesses, including automobiles, robotics, and manufacturing, and its market is growing rapidly. This book helps you explore Detectron2, Facebook's next-gen library providing cutting-edge detection and segmentation algorithms. It's used in research and practical projects at Facebook to support computer vision tasks, and its models can be exported to TorchScript or ONNX for deployment. The book provides you with step-by-step guidance on using existing models in Detectron2 for computer vision tasks (object detection, instance segmentation, key-point detection, semantic detection, and panoptic segmentation). You'll get to grips with the theories and visualizations of Detectron2's architecture and learn how each module in Detectron2 works. As you advance, you'll build your practical skills by working on two real-life projects (preparing data, training models, fine-tuning models, and deployments) for object detection and instance segmentation tasks using Detectron2. Finally, you'll deploy Detectron2 models into production and develop Detectron2 applications for mobile devices. By the end of this deep learning book, you'll have gained sound theoretical knowledge and useful hands-on skills to help you solve advanced computer vision tasks using Detectron2.

Contents:

Cover

Title Page

Copyright and Credits

Dedications

Foreword

Contributors

Table of Contents

Preface

Part 1: Introduction to Detectron2

Chapter 1: An Introduction to Detectron2 and Computer Vision Tasks

Technical requirements

Computer vision tasks

Object detection

Instance segmentation

Keypoint detection

Semantic segmentation

Panoptic segmentation

An introduction to Detectron2 and its architecture

Introducing Detectron2

Detectron2 architecture

Detectron2 development environments

Cloud development environment for Detectron2 applications

Local development environment for Detectron2 applications

Connecting Google Colab to a local development environment

Summary

Chapter 2: Developing Computer Vision Applications Using Existing Detectron2 Models

Introduction to Detectron2's Model Zoo

Developing an object detection application

Getting the configuration file

Getting a predictor

Performing inferences

Visualizing the results

Developing an instance segmentation application

Selecting a configuration file

Developing a keypoint detection application

Developing a panoptic segmentation application

Developing a semantic segmentation application

Selecting a configuration file and getting a predictor

Putting it all together

Performing a computer vision task

Summary.

Part 2: Developing Custom Object Detection Models

Chapter 3: Data Preparation for Object Detection Applications

Common data sources

Getting images

Selecting an image labeling tool

Annotation formats

Labeling the images

Annotation format conversions

Converting YOLO datasets to COCO datasets

Converting Pascal VOC datasets to COCO datasets

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

Introduction to the application architecture

The backbone network

Region Proposal Network

The anchor generator

The RPN head

The RPN loss calculation

Proposal predictions

Region of Interest Heads

The pooler

The box predictor

Chapter 5: Training Custom Object Detection Models

Processing data

The dataset

Downloading and performing initial explorations

Data format conversion

Displaying samples

Using the default trainer

Selecting the best model

Evaluation metrics for object detection models

Inferencing thresholds

Sample predictions

Developing a custom trainer

Utilizing the hook system

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

Inspecting training histories with TensorBoard

Understanding Detectron2's solvers

Gradient descent

Stochastic gradient descent

Momentum

Variable learning rates

Fine-tuning the learning rate and batch size

Chapter 7: Fine-Tuning Object Detection Models

Setting anchor sizes and anchor ratios

Preprocessing input images

Sampling training data and generating the default anchors

Generating sizes and ratios hyperparameters

Setting pixel means and standard deviations.

Preparing a data loader

Calculating the running means and standard deviations

Chapter 8: Image Data Augmentation Techniques

Image augmentation techniques

Why image augmentations?

What are image augmentations?

How to perform image augmentations

Detectron2's image augmentation system

Transformation classes

Augmentation classes

The AugInput class

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

The Detectron2 data loader

Applying existing image augmentation techniques

Developing custom image augmentation techniques

Modifying the existing data loader

Developing the MixUp image augmentation technique

Developing the Mosaic image augmentation technique

Applying test-time image augmentation techniques

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

Chapter 10: Training Instance Segmentation Models

Preparing data for training segmentation models

Getting images, labeling images, and converting annotations

Introduction to the brain tumor segmentation dataset

The architecture of the segmentation models

Training custom segmentation models

Chapter 11: Fine-Tuning Instance Segmentation Models

Introduction to PointRend

Using existing PointRend models

Training custom PointRend models

Part 4: Deploying Detectron2 Models into Production

Chapter 12: Deploying Detectron2 Models into Server Environments

Supported file formats and runtimes

Development environments, file formats, and runtimes

Exporting PyTorch models using the tracing method

When the tracing method fails.

Exporting PyTorch models using the scripting method

Mixing tracing and scripting approaches

Deploying models using a C++ environment

Deploying custom Detectron2 models

Detectron2 utilities for exporting models

Exporting a custom Detectron2 model

Chapter 13: Deploying Detectron2 Models into Browsers and Mobile Environments

Deploying Detectron2 models using ONNX

Introduction to ONNX

Exporting a PyTorch model to ONNX

Loading an ONNX model to the browser

Exporting a custom Detectron2 model to ONNX

Developing mobile computer vision apps with D2Go

Introduction to D2Go

Using existing D2Go models

Training custom D2Go models

Model quantization

Index

Other Books You May Enjoy.

Notes:

Includes index.

Description based on print version record.

ISBN:

9781800566606

1800566603

OCLC:

1375294398