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

The problem with traditional deep neural networks

Before we dive into CNNs, let's look at the major problem that's faced when using traditional deep neural networks.

Let's reconsider the model we built on the Fashion-MNIST dataset in Chapter 3, Building a Deep Neural Network with PyTorch. We will fetch a random image and predict the class that corresponds to that image, as follows:

The code for this section is available as Issues_with_image_translation.ipynb in the Chapter04 folder of this book's GitHub repository - . Note that the entire code is available in GitHub and that only the additional code corresponding to the issue of image translation will be discussed here for brevity. We strongly encourage you to refer to the notebooks in this book's GitHub repository while executing the code.
  1. Fetch a random image from the available training images:
# Note that you should run the code in 
# Batch size of 32 section in Chapter 3
# before...