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

Building blocks of a CNN

CNNs are the most prominent architectures that are used when working on images. CNNs address the major limitations of deep neural networks that we saw in the previous section. Besides image classification, they also help with object detection, image segmentation, GANs, and many more essentially, wherever we use images. Furthermore, there are different ways of constructing a convolutional neural network, and there are multiple pre-trained models that leverage CNNs to perform various tasks. Starting with this chapter, we will be using CNNs extensively.

In the upcoming subsections, we will understand the fundamental building blocks of a CNN, which are as follows:

  • Convolutions
  • Filters
  • Strides and padding
  • Pooling

Let's get started!


A convolution is basically multiplication between two matrices. As you saw in the previous chapter, matrix multiplication is a key ingredient of training a neural network. (We perform matrix multiplication when...