Computer Vision Projects with PyTorch: Design and Develop Production-Grade Models
Akshay / Shivananda Kulkarni
346 pages, parution le 18/07/2022
Résumé
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
Chapter 2: Building Image Classification ModelChapter Goal: The chapter will discuss about image classification model along with data augmentation techniques.No of pages: 40Sub - Topics 1. Data preparation for image classification problem2. Data augmentation techniques3. Setting up model architecture with explanation4. Train and run inference for the Image Classification model5. Discuss Grouped Convolution, Dilated Convolution and transposed convolution and their application
Chapter 3: Building Object Detection ModelChapter Goal: This chapter will explain the core difference between simple classification model to detecting objects in an image. We will understand optimizing loss function to get the final object localized and detected. The chapter will take through some concepts of the existing models and how to fine tune them.No of pages: 30Sub - Topics: 1. Exploring Object Detection concepts like FastRCNN, YOLO2. Explaining annotations and examples of how annotations are used in Object Detection3. Explaining loss function components4. Building Object Detection model, using transfer learning technique5. Running inference on fine-tuned model
Chapter 4: Building Image Segmentation ModelChapter Goal: The chapter will define how single or multiple images can be segmented in an image. How a user can define a loss function and develop a model to segregate image outlines. No of pages: 35Sub - Topics: 1. Concepts on how segmentation works on Images2. Explaining custom pre trained models3. Defining and explaining loss functions4. Implementing & fine-tuning Image Segmentation model
Chapter 5: Image Similarity & Image based SearchChapter Goal: The chapter deals with the explanation of how the image similarity works and how use cases move around this concept. No of pages: 25Sub - Topics: 1. Defining Image similarity and anomaly problems for images2. Defining the datasets3. Defining the loss functions and methodologies4. Providing solutions for Detecting Image similarities
Chapter 6: Image Anomaly DetectionChapter Goal: The chapter deals with the explanation of how anomalies from images can be detected and use-cases around it.No of pages: 20Sub - Topics: 1. Defining anomaly problems for images2. Defining the datasets3. Defining the loss functions and methodologies4. Detecting anomalies on images
Chapter 7: Video Processing Applications using PyTorchChapter Goal: This chapter deals with various mechanism of video processing techniques. This chapter will help one to deal with untangling the complexities of video with series of images placed in time sequence. Concepts of RNN/LSTM/GRU will be discussed to solve real time use-cases on videos.No of pages: 50Sub - Topics: 1. Setting up concepts of time dependent feature set2. Extrapolating images to videos3. Setting up concepts for video processing using Convolutional Neural Networks4. Defining the dataset and the loss function5. Defining the model6. Training the model and run inference
Chapter 8: Super-resolution through Upscaling & GANChapter Goal: This chapter deals with foundations on Generative Adversarial Networks in the field of computer vision. The concepts will be extrapolated with an use-case to how it is being used in super resolution (Enhancing Image Quality)No of pages: 30Sub - Topics: 1. Establish the concept of upscaling in images1. Foundations of VAE and GAN in images2. Setting up codes in GAN for super resolution3. Using the concept to understand data augmentation using GAN
Chapter 9: Body Posture DetectionChapter Goal: This chapter will establish the concept of multiple body posture detection. It will have the code encompassed the detection and multiple methods around posture detection applications.No of pages: 30Sub - Topics: 1. Discussing top-down and bottom-up approach to detect persons2. Discuss open pose detection model to establish body pose3. Use of segmentation technique to detect body pose
Chapter 10: Explainable AI for Computer Vision using GRADCAMChapter Goal: This chapter deals with foundations on how a deep learning model results can be explained. An overview of GRADCAM and how the concepts help someone explaining a Computer Vision model will be discussed in abundance.No of pages: 15Sub - Topics: 1. Revisit the concepts of explain-able AI2. Deep learning explainers to CV classification model3. Setting up concepts of GRADCAM4. Implementing how Computer Vision models can be interpreted by GRADCAM
Adarsha Shivananda is a senior data scientist on Indegene's product and technology team where he works on building machine learning and artificial intelligence (AI) capabilities for pharma products. He aims to build a pool of exceptional data scientists within and outside of the organization to solve problems through training programs, and always wants to stay ahead of the curve. Previously, he worked with Tredence Analytics and IQVIA. He has worked extensively in the pharma, healthcare, retail, and marketing domains. He lives in Bangalore and loves to read and teach data science.
Nitin Ranjan Sharma is a manager at Novartis, involved in leading a team to develop products using multi-modal techniques. He has been a consultant developing solutions for Fortune 500 companies, involved in solving complex business problems using machine learning and deep learning frameworks. His major focus area and core expertise are computer vision and solving some of the challenging business problems dealing with images and video data. Before Novartis, he was part of the data science team at Publicis Sapient, EY, and TekSystems Global Services. He is a regular speaker at data science communities and meet-ups and also an open-source contributor. He has also been training and mentoring data science enthusiasts.
Caractéristiques techniques
| PAPIER | |
| Éditeur(s) | Apress |
| Auteur(s) | Akshay / Shivananda Kulkarni |
| Parution | 18/07/2022 |
| Nb. de pages | 346 |
| EAN13 | 9781484282724 |
Avantages Eyrolles.com
Livraison à partir de 0,01 € en France métropolitaine
Paiement en ligne SÉCURISÉ
Livraison dans le monde
Retour sous 15 jours
+ d'un million et demi de livres disponibles
Consultez aussi
- Les meilleures ventes en Graphisme & Photo
- Les meilleures ventes en Informatique
- Les meilleures ventes en Construction
- Les meilleures ventes en Entreprise & Droit
- Les meilleures ventes en Sciences
- Les meilleures ventes en Littérature
- Les meilleures ventes en Arts & Loisirs
- Les meilleures ventes en Vie pratique
- Les meilleures ventes en Voyage et Tourisme
- Les meilleures ventes en BD et Jeunesse
