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

Classifying images using deep CNNs

So far, we have seen that the traditional neural network predicts incorrectly for translated images. This needs to be addressed because in real-world scenarios, various augmentations will need to be applied, such as translatation and rotation, that were not seen during the training phase. In this section, we will understand how CNNs address the problem of incorrect predictions when image translation happens on images in the Fashion-MNIST dataset.

The pre-processing portion of the Fashion-MNIST dataset remains the same as in the previous chapter, except that when we reshape (.view) the input data, instead of flattening the input to 28 x 28 = 784 dimensions, we reshape the input to a shape of (1,28,28) for each image (remember, channels are to be specified first, followed by their height and width, in PyTorch):

The code for this section is available as CNN_on_FashionMNIST.ipynb in the Chapter04 folder of this book's GitHub repository - https://tinyurl...