Book Image

Modern Computer Vision with PyTorch

By : V Kishore Ayyadevara, Yeshwanth Reddy
5 (2)
Book Image

Modern Computer Vision with PyTorch

5 (2)
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)
1
Section 1 - Fundamentals of Deep Learning for Computer Vision
5
Section 2 - Object Classification and Detection
13
Section 3 - Image Manipulation
17
Section 4 - Combining Computer Vision with Other Techniques

Generating CAMs

Imagine a scenario where you have built a model that is able to make good predictions. However, the stakeholder that you are presenting the model to wants to understand the reason why the model predictions are as they are. CAMs come in handy in this scenario. An example CAM is as follows, where we have the input image on the left and the pixels that were used to come up with the class prediction highlighted on the right:

Let's understand how CAMs can be generated once a model is trained. Feature maps are intermediate activations that come after a convolution operation. Typically, the shape of these activation maps is n-channels x height x width. If we take the mean of all these activations, they show the hotspots of all the classes in the image. But if we are interested in locations that are only important for a particular class (say, cat), we need to figure out only those feature maps among n-channels that are responsible for that class. For the convolution layer...