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 semantic segmentation using U-Net

In this section, we'll leverage the U-Net architecture to predict the class that corresponds to all the pixels in the image. A sample of such an input-output combination is as follows:

Note that, in the preceding picture, the objects that belong to the same class (in the left image – the input image) have the same pixel value (in the right image – the output image), which is why we are segmenting the pixels that are semantically similar to each other. This is also known as semantic segmentation.

Now, let's learn how to code semantic segmentation:

The following code is available as Semantic_Segmentation_with_U_Net.ipynb in the Chapter09 folder of this book's GitHub repository - The code contains URLs to download data from and is moderately lengthy.
  1. Let's begin by downloading the necessary datasets, installing the necessary packages, and then importing them. Once we've...