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 CNN for classifying real-world images

So far, we have learned how to perform image classification on the Fashion-MNIST dataset. In this section, we'll do the same for a more real-world scenario, where the task is to classify images containing cats or dogs. We will also learn about how the accuracy of the dataset varies when we change the number of images available for training.

We will be working on a dataset available in Kaggle:

The code for this section is available as Cats_Vs_Dogs.ipynb in the Chapter04 folder of this book's GitHub repository - Be sure to copy the URL from the notebook in GitHub to avoid any issue while reproducing the results
  1. Import the necessary packages:
import torchvision
import torch.nn as nn
import torch
import torch.nn.functional as F
from torchvision import transforms,models,datasets
from PIL import Image
from torch import optim
device = 'cuda' if torch.cuda...