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

Understanding the impact of varying the learning rate

So far, we have been using a learning rate of 0.01 while training our models. In Chapter 1, Artificial Neural Network Fundamentals, we learned that the learning rate plays a key role in attaining optimal weight values. Here, the weight values gradually move toward the optimal value when the learning rate is small, while the weight value oscillates at a non-optimal value when the learning rate is large. We worked on a toy dataset in Chapter 1, Artificial Neural Network Fundamentals, so we will work on a realistic scenario in this section.

To understand the impact of the varying learning rate, we'll go through the following scenario:

  • Higher learning rate (0.1) on a scaled dataset
  • Lower learning rate (0.00001) on a scaled dataset
  • Lower learning rate (0.001) on a non-scaled dataset
  • Higher learning rate (0.1) on a non-scaled dataset

Overall, in this section, we'll be learning about the impact that various learning rate values...