You're reading from Mastering PyTorch Build powerful neural network architectures using advanced PyTorch 1.x features

Product type Paperback

Published in Feb 2021

Publisher Packt

ISBN-13 9781789614381

Length 450 pages

Edition 1st Edition

Languages

Python

Tools

PyTorch

Concepts

Deep Learning

Author (1):

Ashish Ranjan Jha

View More author details

Table of Contents (20) Chapters

Preface

1. Section 1: PyTorch Overview

2. Chapter 1: Overview of Deep Learning using PyTorch FREE CHAPTER

3. Chapter 2: Combining CNNs and LSTMs

4. Section 2: Working with Advanced Neural Network Architectures

5. Chapter 3: Deep CNN Architectures

6. Chapter 4: Deep Recurrent Model Architectures

7. Chapter 5: Hybrid Advanced Models

8. Section 3: Generative Models and Deep Reinforcement Learning

9. Chapter 6: Music and Text Generation with PyTorch

10. Chapter 7: Neural Style Transfer

11. Chapter 8: Deep Convolutional GANs

12. Chapter 9: Deep Reinforcement Learning

13. Section 4: PyTorch in Production Systems

14. Chapter 10: Operationalizing PyTorch Models into Production

15. Chapter 11: Distributed Training

16. Chapter 12: PyTorch and AutoML

17. Chapter 13: PyTorch and Explainable AI

18. Chapter 14: Rapid Prototyping with PyTorch

19. Other Books You May Enjoy

Leave a review - let other readers know what you think

Fine-tuning the AlexNet model

In this section, we will first take a quick look at the AlexNet architecture and how to build one by using PyTorch. Then we will explore PyTorch's pre-trained CNN models repository, and finally, use a pre-trained AlexNet model for fine-tuning on an image classification task, as well as making predictions.

AlexNet is a successor of LeNet with incremental changes in the architecture, such as 8 layers (5 convolutional and 3 fully connected) instead of 5, and 60 million model parameters instead of 60,000, as well as using MaxPool instead of AvgPool. Moreover, AlexNet was trained and tested on a much bigger dataset – ImageNet, which is over 100 GB in size, as opposed to the MNIST dataset (on which LeNet was trained), which amounts to a few MBs. AlexNet truly revolutionized CNNs as it emerged as a significantly more powerful class of models on image-related tasks than the other classical machine learning models, such as SVMs. Figure 3.14 shows...