book

Mastering PyTorch

Name: Mastering PyTorch
Author: Ashish Ranjan Jha
ISBN: 9781789614381

by Ashish Ranjan Jha

February 2021

Intermediate to advanced

450 pages

9h 6m

English

Packt Publishing

Read now

Unlock full access

Mastering PyTorch
Why subscribe?ForewordContributorsAbout the authorAbout the reviewerPackt is searching for authors like you
Preface
Who this book is forWhat this book coversTo get the most out of this bookDownload the example code filesDownload the color imagesConventions usedGet in touchReviews
Section 1: PyTorch Overview
Chapter 1: Overview of Deep Learning using PyTorch
Technical requirementsA refresher on deep learningActivation functionsOptimization scheduleExploring the PyTorch libraryPyTorch modulesTensor modulesTraining a neural network using PyTorchSummary
Chapter 2: Combining CNNs and LSTMs
Technical requirementsBuilding a neural network with CNNs and LSTMsText encoding demoBuilding an image caption generator using PyTorchDownloading the image captioning datasetsPreprocessing caption (text) dataPreprocessing image dataDefining the image captioning data loaderDefining the CNN-LSTM modelTraining the CNN-LSTM modelGenerating image captions using the trained modelSummary
Section 2: Working with Advanced Neural Network Architectures
Chapter 3: Deep CNN Architectures
Technical requirements Why are CNNs so powerful?Evolution of CNN architecturesDeveloping LeNet from scratchUsing PyTorch to build LeNetTraining LeNetTesting LeNetFine-tuning the AlexNet modelUsing PyTorch to fine-tune AlexNetRunning a pre-trained VGG modelExploring GoogLeNet and Inception v3Inception modules1x1 convolutionsGlobal average poolingAuxiliary classifiersInception v3Discussing ResNet and DenseNet architecturesDenseNetUnderstanding EfficientNets and the future of CNN architecturesSummary
Chapter 4: Deep Recurrent Model Architectures
Technical requirementsExploring the evolution of recurrent networksTypes of recurrent neural networksRNNsBidirectional RNNsLSTMsExtended and bidirectional LSTMsMulti-dimensional RNNsStacked LSTMsGRUsGrid LSTMsGated orthogonal recurrent unitsTraining RNNs for sentiment analysisLoading and preprocessing the text datasetInstantiating and training the modelBuilding a bidirectional LSTMLoading and preprocessing text datasetInstantiating and training the LSTM modelDiscussing GRUs and attention-based modelsGRUs and PyTorchAttention-based modelsSummary
Chapter 5: Hybrid Advanced Models
Technical requirementsBuilding a transformer model for language modelingReviewing language modelingUnderstanding the transformer model architectureDeveloping a RandWireNN model from scratchUnderstanding RandWireNNsDeveloping RandWireNNs using PyTorchSummary
Section 3: Generative Models and Deep Reinforcement Learning

Chapter 6: Music and Text Generation with PyTorch
Technical requirementsBuilding a transformer-based text generator with PyTorchTraining the transformer-based language modelSaving and loading the language modelUsing the language model to generate textUsing a pre-trained GPT-2 model as a text generatorOut-of-the-box text generation with GPT-2Text generation strategies using PyTorchGenerating MIDI music with LSTMs using PyTorchLoading the MIDI music data Defining the LSTM model and training routineTraining and testing the music generation modelSummary
Chapter 7: Neural Style Transfer
Technical requirementsUnderstanding how to transfer style between imagesImplementing neural style transfer using PyTorchLoading the content and style imagesLoading and trimming the pre-trained VGG19 modelBuilding the neural style transfer modelTraining the style transfer modelExperimenting with the style transfer systemSummary
Chapter 8: Deep Convolutional GANs
Technical requirementsDefining the generator and discriminator networksUnderstanding the DCGAN generator and discriminator Training a DCGAN using PyTorchDefining the generatorDefining the discriminatorLoading the image datasetTraining loops for DCGANsUsing GANs for style transferUnderstanding the pix2pix architectureSummary
Chapter 9: Deep Reinforcement Learning
Technical requirementsReviewing reinforcement learning conceptsTypes of reinforcement learning algorithmsDiscussing Q-learningUnderstanding deep Q-learningUsing two separate DNNsExperience replay bufferBuilding a DQN model in PyTorchInitializing the main and target CNN modelsDefining the experience replay bufferSetting up the environmentDefining the CNN optimization functionManaging and running episodesTraining the DQN model to learn PongSummary
Section 4: PyTorch in Production Systems
Chapter 10: Operationalizing PyTorch Models into Production
Technical requirementsModel serving in PyTorchCreating a PyTorch model inference pipelineBuilding a basic model serverCreating a model microserviceServing a PyTorch model using TorchServeInstalling TorchServeLaunching and using a TorchServe serverExporting universal PyTorch models using TorchScript and ONNXUnderstanding the utility of TorchScriptModel tracing with TorchScriptModel scripting with TorchScriptRunning a PyTorch model in C++Using ONNX to export PyTorch modelsServing PyTorch models in the cloudUsing PyTorch with AWSServing PyTorch model on Google CloudServing PyTorch models with AzureSummaryReferences
Chapter 11: Distributed Training
Technical requirementsDistributed training with PyTorchTraining the MNIST model in a regular fashionTraining the MNIST model in a distributed fashionDistributed training on GPUs with CUDASummary
Chapter 12: PyTorch and AutoML
Technical requirementsFinding the best neural architectures with AutoMLUsing Auto-PyTorch for optimal MNIST model search Using Optuna for hyperparameter searchDefining the model architecture and loading datasetDefining the model training routine and optimization scheduleRunning Optuna's hyperparameter searchSummary
Chapter 13: PyTorch and Explainable AI
Technical requirementsModel interpretability in PyTorchTraining the handwritten digits classifier – a recapVisualizing the convolutional filters of the modelVisualizing the feature maps of the modelUsing Captum to interpret modelsSetting up CaptumExploring Captum's interpretability toolsSummary
Chapter 14: Rapid Prototyping with PyTorch
Technical requirementsUsing fast.ai to set up model training in a few minutesSetting up fast.ai and loading dataTraining a MNIST model using fast.aiEvaluating and interpreting the model using fast.aiTraining models on any hardware using PyTorch LightningDefining the model components in PyTorch LightningTraining and evaluating the model using PyTorch LightningSummary
Other Books You May Enjoy
Leave a review - let other readers know what you think

Overview

Dive into the world of modern deep learning with 'Mastering PyTorch.' This book guides you through the latest techniques, enabling you to build and deploy sophisticated neural network architectures in PyTorch 1.x. Whether you are working on NLP, computer vision, or reinforcement learning projects, this comprehensive guide takes you step-by-step from fundamentals to advanced implementation.

What this Book will help me do

Learn to design and train advanced deep learning models such as transformers, GANs, and ResNets using PyTorch.
Develop and deploy natural language processing (NLP) pipelines and models.
Master generative art and style transfer techniques for creating music, images, and text.
Implement distributed training methodologies and effectively scale deep learning workloads.
Gain practical knowledge in deploying PyTorch models into production systems and applications.

Author(s)

Ashish Ranjan Jha, the author of 'Mastering PyTorch,' is a deep learning practitioner and educator with extensive experience in applying neural network architectures to real-world problems. His approachable style and clear explanations make complex topics accessible to a wide audience. Ashish's passion for teaching technical topics shines in this deeply practical guide.

Who is it for?

This book is ideal for data scientists, machine learning engineers, and deep learning enthusiasts who aim to bring their skill set to the next level. If you have a foundational understanding of Python and basic deep learning concepts, this guide will help you master PyTorch and implement advanced neural network architectures. Whether you're seeking to innovate in NLP, computer vision, or other AI fields, 'Mastering PyTorch' is tailored for you.

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781789614381

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills