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 loss optimizer

So far, we have been optimizing loss based on the Adam optimizer. In this section, we will do the following:

  • Modify the optimizer so that it becomes a Stochastic Gradient Descent (SGD) optimizer
  • Revert to a batch size of 32 while fetching data in the DataLoader
  • Increase the number of epochs to 10 (so that we can compare the performance of SGD and Adam over a longer number of epochs)

Making these changes means that only one step in the Batch size of 32 section will change (since the batch size is already 32 in the Batch size of 32 section); that is, we will modify the optimizer so that it's the SGD optimizer.

Let's modify the get_model function in step 4 of the Batch size of 32 section in order to modify the optimzier so that we're using the SGD optimizer instead, as follows:

The following code is available as Varying_loss_optimizer.ipynb in the Chapter03 folder of this book's GitHub repository - https://tinyurl...