Book Image

Modern Computer Vision with PyTorch

By : V Kishore Ayyadevara, Yeshwanth Reddy
Book Image

Modern Computer Vision with PyTorch

By: V Kishore Ayyadevara, Yeshwanth Reddy

Overview of this book

Deep 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.
Table of Contents (25 chapters)
Section 1 - Fundamentals of Deep Learning for Computer Vision
Section 2 - Object Classification and Detection
Section 3 - Image Manipulation
Section 4 - Combining Computer Vision with Other Techniques

Learning the basics of reinforcement learning

Reinforcement learning (RL) is an area of machine learning concerned with how software agents ought to take actions in a given state of an environment to maximize the notion of cumulative reward.

To understand how RL helps, let's consider a simple scenario. Imagine that you are playing chess against a computer (in our case, the computer is an agent that has learned/is learning how to play chess). The setup (rules) of the game constitutes the environment. Furthermore, as we make a move (take an action), the state of the board (the location of various pieces on the chessboard) changes. At the end of the game, depending on the result, the agent gets a reward. The objective of the agent is to maximize the reward.

If the machine (agent1) is playing against a human, the number of games that it can play is finite (depending on the number of games the human can play). This might create a bottleneck for the agent to learn well. However, what...