What do you think?
Rate this book
Modern Computer Vision with PyTorch: Explore deep learning concepts and implement over 50 real-world image applications
Get to grips with deep learning techniques for building image processing applications using PyTorch with the help of code notebooks and test questions
Key FeaturesImplement solutions to 50 real-world computer vision applications using PyTorchUnderstand the theory and working mechanisms of neural network architectures and their implementationDiscover best practices using a custom library created especially for this bookBook DescriptionDeep learning is the driving force behind many recent advances in various computer vision (CV) applications. This book takes a hands-on approach to help you to solve over 50 CV problems using PyTorch1.x on real-world datasets.
You’ll start by building a neural network (NN) from scratch using NumPy and PyTorch and discover best practices for tweaking its hyperparameters. You’ll then perform image classification using convolutional neural networks and transfer learning and understand how they work. As you progress, you’ll implement multiple use cases of 2D and 3D multi-object detection, segmentation, human-pose-estimation by learning about the R-CNN family, SSD, YOLO, U-Net architectures, and the Detectron2 platform. The book will also guide you in performing facial expression swapping, generating new faces, and manipulating facial expressions as you explore autoencoders and modern generative adversarial networks. You’ll learn how to combine CV with NLP techniques, such as LSTM and transformer, and RL techniques, such as Deep Q-learning, to implement OCR, image captioning, object detection, and a self-driving car agent. Finally, you'll move your NN model to production on the AWS Cloud.
By the end of this book, you’ll be able to leverage modern NN architectures to solve over 50 real-world CV problems confidently.
What you will learnTrain a NN from scratch with NumPy and PyTorchImplement 2D and 3D multi-object detection and segmentationGenerate digits and DeepFakes with autoencoders and advanced GANsManipulate images using CycleGAN, Pix2PixGAN, StyleGAN2, and SRGANCombine CV with NLP to perform OCR, image captioning, and object detectionCombine CV with reinforcement learning to build agents that play pong and self-drive a carDeploy a deep learning model on the AWS server using FastAPI and DockerImplement over 35 NN architectures and common OpenCV utilitiesWho this book is forThis book is for beginners to PyTorch and intermediate-level machine learning practitioners who are looking to get well-versed with computer vision techniques using deep learning and PyTorch. If you are just getting started with neural networks, you’ll find the use cases accompanied by notebooks in GitHub present in this book useful. Basic knowledge of the Python programming language and machine learning is all you need to get started with this book.
Table of ContentsArtificial Neural Network FundamentalsPyTorch FundamentalsBuilding a Deep Neural Network with PyTorchIntroducing Convolutional Neural NetworksTransfer Learning for object ClassificationPractical Aspects of Image ClassificationBasics of Object detectionAdvanced object detectionImage segmentationApplications of object detection and localizationAutoencoders and Image ManipulationImage generation using
Key FeaturesImplement solutions to 50 real-world computer vision applications using PyTorchUnderstand the theory and working mechanisms of neural network architectures and their implementationDiscover best practices using a custom library created especially for this bookBook DescriptionDeep learning is the driving force behind many recent advances in various computer vision (CV) applications. This book takes a hands-on approach to help you to solve over 50 CV problems using PyTorch1.x on real-world datasets.
You’ll start by building a neural network (NN) from scratch using NumPy and PyTorch and discover best practices for tweaking its hyperparameters. You’ll then perform image classification using convolutional neural networks and transfer learning and understand how they work. As you progress, you’ll implement multiple use cases of 2D and 3D multi-object detection, segmentation, human-pose-estimation by learning about the R-CNN family, SSD, YOLO, U-Net architectures, and the Detectron2 platform. The book will also guide you in performing facial expression swapping, generating new faces, and manipulating facial expressions as you explore autoencoders and modern generative adversarial networks. You’ll learn how to combine CV with NLP techniques, such as LSTM and transformer, and RL techniques, such as Deep Q-learning, to implement OCR, image captioning, object detection, and a self-driving car agent. Finally, you'll move your NN model to production on the AWS Cloud.
By the end of this book, you’ll be able to leverage modern NN architectures to solve over 50 real-world CV problems confidently.
What you will learnTrain a NN from scratch with NumPy and PyTorchImplement 2D and 3D multi-object detection and segmentationGenerate digits and DeepFakes with autoencoders and advanced GANsManipulate images using CycleGAN, Pix2PixGAN, StyleGAN2, and SRGANCombine CV with NLP to perform OCR, image captioning, and object detectionCombine CV with reinforcement learning to build agents that play pong and self-drive a carDeploy a deep learning model on the AWS server using FastAPI and DockerImplement over 35 NN architectures and common OpenCV utilitiesWho this book is forThis book is for beginners to PyTorch and intermediate-level machine learning practitioners who are looking to get well-versed with computer vision techniques using deep learning and PyTorch. If you are just getting started with neural networks, you’ll find the use cases accompanied by notebooks in GitHub present in this book useful. Basic knowledge of the Python programming language and machine learning is all you need to get started with this book.
Table of ContentsArtificial Neural Network FundamentalsPyTorch FundamentalsBuilding a Deep Neural Network with PyTorchIntroducing Convolutional Neural NetworksTransfer Learning for object ClassificationPractical Aspects of Image ClassificationBasics of Object detectionAdvanced object detectionImage segmentationApplications of object detection and localizationAutoencoders and Image ManipulationImage generation using
826 pages, Kindle Edition
Published November 27, 2020
20 people are currently reading
49 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 3 of 3 reviews
August 25, 2025
I bought a hard copy of this book quite some time ago but only going through it these two days. Overall, I would say it may be good for refreshing various topics for computer vision and perception. On the other hand, the materials are vastly outdated by SoTA models nowadays (most of the SoTA CV models are now transformers). Also it is lengthy but not particularly useful for understanding detailed architecture of the various CV models and things that matter such as loss engineering, offline/online evaluation. I would rather save many pages of repeated codes on the training loop and custom dataset classes. If i would like to get an implementation of object detection, tons of code on internet can do that. For me, i don't need to have all those code snippets in one place as a book.
October 19, 2022
This is amazing
This entire review has been hidden because of spoilers.
December 23, 2022
See book review here: https://bifarinthefifth.substack.com/...
Displaying 1 - 3 of 3 reviews