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

Introducing LSTM architecture

In the previous section, we learned about how a traditional RNN faces a vanishing or exploding gradient problem resulting in it not being able to accommodate long-term memory. In this section, we will learn about how to leverage LSTM to get around this problem.

In order to further understand the scenario with an example, let's consider the following sentence:

I am from England. I speak __.

In the preceding sentence, intuitively, we know that the majority of the people from England speak English. The blank value to be filled (English) is obtained from the fact that the person is from England. While in this scenario we have the signaling word (England) closer to the blank value, in a realistic scenario, we might find that the signal word is far away from the blank space (the word we are trying to predict). When the distance between the signal word and blank value is large, the predictions through traditional RNNs might be wrong because of the vanishing...