Search icon
Arrow left icon
All Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Newsletters
Free Learning
Arrow right icon
Mastering PyTorch

You're reading from  Mastering PyTorch

Product type Book
Published in Feb 2021
Publisher Packt
ISBN-13 9781789614381
Pages 450 pages
Edition 1st Edition
Languages
Author (1):
Ashish Ranjan Jha Ashish Ranjan Jha
Profile icon Ashish Ranjan Jha

Table of Contents (20) Chapters

Preface Section 1: PyTorch Overview
Chapter 1: Overview of Deep Learning using PyTorch Chapter 2: Combining CNNs and LSTMs Section 2: Working with Advanced Neural Network Architectures
Chapter 3: Deep CNN Architectures Chapter 4: Deep Recurrent Model Architectures Chapter 5: Hybrid Advanced Models Section 3: Generative Models and Deep Reinforcement Learning
Chapter 6: Music and Text Generation with PyTorch Chapter 7: Neural Style Transfer Chapter 8: Deep Convolutional GANs Chapter 9: Deep Reinforcement Learning Section 4: PyTorch in Production Systems
Chapter 10: Operationalizing PyTorch Models into Production Chapter 11: Distributed Training Chapter 12: PyTorch and AutoML Chapter 13: PyTorch and Explainable AI Chapter 14: Rapid Prototyping with PyTorch Other Books You May Enjoy

Using Optuna for hyperparameter search

Optuna is one of the hyperparameter search tools that supports PyTorch. You can read in detail about the search strategies used by the tool, such as TPE (Tree-Structured Parzen Estimation) and CMA-ES (Covariance Matrix Adaptation Evolution Strategy) in the Optuna paper, at https://arxiv.org/pdf/1907.10902.pdf. Besides the advanced hyperparameter search methodologies, the tool provides a sleek API, which we will explore in a moment.

Tool citation

Optuna: A Next-Generation Hyperparameter Optimization Framework.

Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, and Masanori Koyama (2019, in KDD).

In this section, we will once again build and train the MNIST model, this time using Optuna to figure out the optimal hyperparameter setting. We will discuss important parts of the code step by step, in the form of an exercise. The full code can be found here:

https://github.com/PacktPublishing/Mastering-PyTorch/blob/master/Chapter12...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $15.99/month. Cancel anytime}