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

Building a deeper neural network

So far, our neural network architecture only has one hidden layer. In this section, we will contrast the performance of models where there are two hidden layers and no hidden layer (with no hidden layer being a logistic regression).

A model with two layers within a network can be built as follows (note that we have kept the number of units in the second hidden layer set to 1,000). The modified get_model function (from the code in the Batch size of 32 section), where there are two hidden layers, is as follows:

The following code is available as Impact_of_building_a_deeper_neural_network.ipynb in the Chapter03 folder of this book's GitHub repository - . Note that we are not providing all the steps for brevity and that only the steps where there is a change from the code we went through in the Batch size of 32 section will be discussed in the following code. We encourage you to refer to the notebooks in this book's...