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

Exploring the Mask R-CNN architecture

The Mask R-CNN architecture helps in identifying/highlighting the instances of objects of a given class within an image. This comes in especially handy when there are multiple objects of the same type present within the image. Furthermore, the term Mask represents the segmentation that's done at the pixel level by Mask R-CNN.

The Mask R-CNN architecture is an extension of the Faster R-CNN network, which we learned about in the previous chapter. However, a few modifications have been made to the Mask R-CNN architecture, as follows:

  • The RoI Pooling layer has been replaced with the RoI Align layer.
  • A mask head has been included to predict a mask of objects in addition to the head, which already predicts the classes of objects and bounding box correction in the final layer.
  • A fully convolutional network (FCN) is leveraged for mask prediction.

Let's have a quick look at the events that occur within Mask R-CNN before we understand how each of...