Computer vision projects with PyTorch : design and develop production-grade models / / Akshay Kulkarni, Adarsha Shivananda, Nitin Ranjan Sharma

• Autore: Kulkarni Akshay
• Pubblicazione: New York, New York : , : Apress, , [2022]; ©2022
• Descrizione fisica: 1 online resource (355 pages)
• Disciplina: 006.37
• Soggetto topico: Computer vision; Pattern recognition systems; Machine learning
• Persona (resp. second.): ShivanandaAdarsha; SharmaNitin Ranjan
• Note generali: Includes index.
• Nota di contenuto: Intro -- Table of Contents -- About the Authors -- About the Technical Reviewer -- Introduction -- Chapter 1: The Building Blocks of Computer Vision -- What Is Computer Vision -- Applications -- Classification -- Object Detection and Localization -- Image Segmentation -- Anomaly Detection -- Video Analysis -- Channels -- Convolutional Neural Networks -- Receptive Field -- Local Receptive Field -- Global Receptive Field -- Pooling -- Max Pooling -- Average Pooling -- Global Average Pooling -- Calculation: Feature Map and Receptive Fields -- Kernel -- Stride -- Pooling -- Padding -- Input and Output -- Calculation of Receptive Field -- Understanding the CNN Architecture Type -- Understanding Types of Architecture -- AlexNet -- VGG -- ResNet -- Inception Architectures -- Working with Deep Learning Model Techniques -- Batch Normalization -- Dropouts -- Data Augmentation Techniques -- Introduction to PyTorch -- Installation -- Basic Start -- Summary -- Chapter 2: Image Classification -- Topics to Cover -- Defining the Problem -- Overview of the Approach -- Creating an Image Classification Pipeline -- First Basic Model -- Data -- Data Exploration -- Data Loader -- Define the Model -- The Training Process -- The Second Variation of Model -- The Third Variation of the Model -- The Fourth Variation of the Model -- Summary -- Chapter 3: Building an Object Detection Model -- Object Detection Using Boosted Cascade -- R-CNN -- The Region Proposal Network -- Fast Region-Based Convolutional Neural Network -- How the Region Proposal Network Works -- The Anchor Generation Layer -- The Region Proposal Layer -- Mask R-CNN -- Prerequisites -- YOLO -- YOLO V2/V3 -- Project Code Snippets -- Step 1: Getting Annotated Data -- Step 2: Fixing the Configuration File and Training -- The Model File -- Summary -- Chapter 4: Building an Image Segmentation Model. ; Image Segmentation -- Pretrained Support from PyTorch -- Semantic Segmentation -- Instance Segmentation -- Fine-Tuning the Model -- Summary -- Chapter 5: Image-Based Search and Recommendation System -- Problem Statement -- Approach and Methodology -- Implementation -- The Dataset -- Installing and Importing Libraries -- Importing and Understanding the Data -- Feature Engineering -- ResNet18 -- Calculating Similarity and Ranking -- Visualizing the Recommendations -- Taking Image Input from Users and Recommending Similar Products -- Summary -- Chapter 6: Pose Estimation -- Top-Down Approach -- Bottom-Up Approach -- OpenPose -- Branch-1 -- Branch-2 -- HRNet (High-Resolution Net) -- Higher HRNet -- PoseNet -- How Does PoseNet Work? -- Single Person Pose Estimation -- Multi-Person Pose Estimation -- Pros and Cons of PoseNet -- Applications of Pose Estimation -- Test Cases Performed Retail Store Videos -- Implementation -- Step 1: Identify the List of Human Keypoints to Track -- Step 2: Identify the Possible Connections Between the Keypoints -- Step 3: Load the Pretrained Model from the PyTorch Library -- Step 4: Input Image Preprocessing and Modeling -- Step 5: Build Custom Functions to Plot the Output -- Step 6: Plot the Output on the Input Image -- Summary -- Chapter 7: Image Anomaly Detection -- Anomaly Detection -- Approach 1: Using a Pretrained Classification Model -- Step 1: Import the Required Libraries -- Step 2: Create the Seed and Deterministic Functions -- Step 3: Set the Hyperparameter -- Step 4: Import the Dataset -- Step 5: Image Preprocessing Stage -- Step 6: Load the Pretrained Model -- Step 7: Freeze the Model -- Step 8: Train the Model -- Step 9: Evaluate the Model -- Approach 2: Using Autoencoder -- Step 1: Prepare the Dataset Object -- Step 2: Build the Autoencoder Network -- Step 3: Train the Autoencoder Network. ; Step 4: Calculate the Reconstruction Loss Based on the Original Data -- Step 5: Select the Most Anomalous Digit Based on the Error Metric Score -- Output -- Summary -- Chapter 8: Image Super-Resolution -- Up-Scaling Using the Nearest Neighbor Concept -- Understanding Bilinear Up-Scaling -- Variational Autoencoders -- Generative Adversarial Networks -- The Model Code -- Model Development -- Imports -- Running the Application -- Summary -- Chapter 9: Video Analytics -- Problem Statement -- Approach -- Implementation -- Data -- Uploading the Required Videos to Google Colab -- Convert the Video to a Series of Images -- Image Extraction -- Data Preparation -- Identify the Hotspots in a Retail Store -- Importing Images -- Getting Crowd Counts -- Security and Surveillance -- Identify the Demographics (Age and Gender) -- Summary -- Chapter 10: Explainable AI for Computer Vision -- Grad-CAM -- Grad-CAM++ -- NBDT -- Step 1 -- Step 2 -- Steps 3 and 4 -- Grad-CAM and Grad-CAM++ Implementation -- Grad-CAM and Grad-CAM++ Implementation on a Single Image -- NBDT Implementation on a Single Image -- Summary -- Index.
• Sommario/riassunto: Design and develop end-to-end, production-grade computer vision projects for real-world industry problems. This book discusses computer vision algorithms and their applications using PyTorch. The book begins with the fundamentals of computer vision: convolutional neural nets, RESNET, YOLO, data augmentation, and other regularization techniques used in the industry. And then it gives you a quick overview of the PyTorch libraries used in the book. After that, it takes you through the implementation of image classification problems, object detection techniques, and transfer learning while training and running inference. The book covers image segmentation and an anomaly detection model. And it discusses the fundamentals of video processing for computer vision tasks putting images into videos. The book concludes with an explanation of the complete model building process for deep learning frameworks using optimized techniques with highlights on model AI explainability. After reading this book, you will be able to build your own computer vision projects using transfer learning and PyTorch. What You Will Learn Solve problems in computer vision with PyTorch. Implement transfer learning and perform image classification, object detection, image segmentation, and other computer vision applications Design and develop production-grade computer vision projects for real-world industry problems Interpret computer vision models and solve business problems Who This Book Is For Data scientists and machine learning engineers interested in building computer vision projects and solving business problems.
• Titolo autorizzato: Computer vision projects with PyTorch
• ISBN: 1-4842-8273-6
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910735390103321
• Lo trovi qui: Univ. Federico II