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)
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

Summary

In this chapter, we learned how the values of various actions in a given state are calculated. We then learned how the agent updates the Q-table using the discounted value of taking an action in a given state. In the process of doing this, we learned how the Q-table is infeasible in a scenario where the number of states is high. We also learned how to leverage deep Q-networks to address the scenario where the number of possible states is high. Next, we moved on to leveraging CNN-based neural networks while building an agent that learned how to play Pong using DQN based on fixed targets. Finally, we learned how to leverage DQN with fixed targets to perform self-driving using the CARLA simulator. As we have seen repeatedly in this chapter, you can use deep Q-learning to learn very different tasks – such as CartPole balancing, playing Pong, and self-driving navigation with almost the same code. While this is not the end of our journey into exploring RL, at this point...