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

Implementing zero-shot learning

Imagine a scenario where I ask you to predict the class of objects in an image where you have not seen an image of the object class earlier. How would you make predictions in such a scenario?

Intuitively, we resort to the attributes of the object in the image and then try to identify the object that matches the most attributes.

In one such scenario where we have to come up with attributes automatically (where the attributes are not given for training), we leverage word vectors. Word vectors encompass semantic similarity among words. For example, all animals would have similar word vectors and automobiles would have very different word vector representations. While the generation of word vectors is out of scope for this book, we will work on pre-trained word vectors. At a very high level, words that have similar surrounding words (context) will have similar vectors. Here's a sample t-SNE representation of word vectors:

From the preceding sample, we...