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

Implementing an agent to perform autonomous driving

Now that you have seen RL working in progressively challenging environments, we will conclude this chapter by demonstrating that the same concepts can be applied to a self-driving car. Since it is impractical to see this working on an actual car, we will resort to a simulated environment. The environment is going to be a full-fledged city of traffic, with cars and additional details within the image of a road. The actor (agent) is a car. The inputs to the car are going to be various sensory inputs such as a dashcam, Light Detection And Ranging (LIDAR) sensors, and GPS coordinates. The outputs are going to be how fast/slow the car will move, along with the level of steering. This simulation will attempt to be an accurate representation of real-world physics. Thus, note that the fundamentals will remain the same, whether it is a car simulation or a real car.

Note that the environment we are going to install needs a graphical user interface...