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

Understanding the impact of varying the batch size

In the previous section, 32 data points were considered per batch in the training dataset. This resulted in a greater number of weight updates per epoch as there were 1,875 weight updates per epoch (60,000/32 is nearly equal to 1,875, where 60,000 is the number of training images).

Furthermore, we did not consider the model's performance on an unseen dataset (validation dataset). We will explore this in this section.

In this section, we will compare the following:

  • The loss and accuracy values of the training and validation data when the training batch size is 32.
  • The loss and accuracy values of the training and validation data when the training batch size is 10,000.

Now that we have brought validation data into the picture, let's rerun the code provided in the Building a neural network section with additional code to generate validation data, as well as to calculate the loss and accuracy values of the validation dataset.