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


In this chapter, we learned how to leverage U-Net and Mask R-CNN to perform segmentation on top of images. We understood how the U-Net architecture can perform downscaling and upscaling on images using convolutions to retain the structure of the image, while still being able to predict masks around objects within an image. We then cemented our understanding of this using the road scene detection exercise, where we segmented the image into multiple classes. Next, we learned about RoI Align, which helps ensure that the issues with RoI pooling surrounding image quantization are addressed. After that, we learned about how Mask R-CNN works so that we could train models to predict instances of people in images, as well as instances of people and tables in an image.

Now that we have a good understanding of various object detection techniques and image segmentation techniques, in the next chapter, we will learn about applications that leverage the techniques we have learned about so far...