book

AI and ML for Coders in PyTorch

Name: AI and ML for Coders in PyTorch
Author: Laurence Moroney
ISBN: 9781098199173

by Laurence Moroney

June 2025

Beginner to intermediate

444 pages

11h 32m

English

O'Reilly Media, Inc.

Read now

Unlock full access

Foreword
Preface
Who Should Read This BookWhy I Wrote This BookNavigating This BookTechnology You Need to UnderstandOnline ResourcesConventions Used in This BookUsing Code ExamplesO’Reilly Online LearningHow to Contact UsAcknowledgments
1. Introduction to PyTorch
What Is Machine Learning?Limitations of Traditional ProgrammingFrom Programming to LearningWhat Is PyTorch?Using PyTorchInstalling PyTorch in PythonUsing PyTorch in PyCharmUsing PyTorch in Google ColabGetting Started with Machine LearningSeeing What the Network LearnedSummary
2. Introduction to Computer Vision
How Computer Vision WorksThe Fashion MNIST DatabaseNeurons for VisionDesigning the Neural NetworkThe Complete CodeTraining the Neural NetworkExploring the Model OutputOverfittingEarly StoppingSummary
3. Going Beyond the Basics: Detecting Features in Images
ConvolutionsPoolingImplementing Convolutional Neural NetworksExploring the Convolutional NetworkBuilding a CNN to Distinguish Between Horses and HumansThe “Horses or Humans” DatasetHandling the DataCNN Architecture for “Horses or Humans”Using the “Horses or Humans” Validation DatasetTesting “Horses or Humans” ImagesImage AugmentationTransfer LearningMulticlass ClassificationDropout RegularizationSummary
4. Using Data with PyTorch
Getting Started with DatasetsExploring the FashionMNIST ClassGeneric Dataset ClassesImageFolderDatasetFolderFakeDataUsing Custom SplitsThe ETL Process for Managing Data in Machine LearningOptimizing the Load PhaseUsing the DataLoader ClassBatchingShufflingParallel Data LoadingCustom Data SamplingParallelizing ETL to Improve Training PerformanceSummary
5. Introduction to Natural Language Processing
Encoding Language into NumbersGetting Started with TokenizationTurning Sentences into SequencesRemoving Stopwords and Cleaning TextStripping Out HTML TagsStripping Out StopwordsStripping Out PunctuationWorking with Real Data SourcesGetting Text DatasetsGetting Text from CSV FilesGetting Text from JSON FilesSummary
6. Making Sentiment Programmable by Using Embeddings
Establishing Meaning from WordsA Simple Example: Positives and NegativesGoing a Little Deeper: VectorsEmbeddings in PyTorchBuilding a Sarcasm Detector by Using EmbeddingsReducing Overfitting in Language ModelsPutting It All TogetherUsing the Model to Classify a SentenceVisualizing the EmbeddingsUsing Pretrained EmbeddingsSummary
7. Recurrent Neural Networks for Natural Language Processing
The Basis of RecurrenceExtending Recurrence for LanguageCreating a Text Classifier with RNNsStacking LSTMsUsing Pretrained Embeddings with RNNsSummary
8. Using ML to Create Text
Turning Sequences into Input SequencesCreating the ModelGenerating TextPredicting the Next WordCompounding Predictions to Generate TextExtending the DatasetImproving the Model ArchitectureEmbedding DimensionsInitializing the LSTMsVariable Learning RateImproving the DataCharacter-Based EncodingSummary

9. Understanding Sequence and Time Series Data
Common Attributes of Time SeriesTrendSeasonalityAutocorrelationNoiseTechniques for Predicting Time SeriesNaive Prediction to Create a BaselineMeasuring Prediction AccuracyLess Naive Predictions: Using a Moving Average for PredictionImproving the Moving-Average AnalysisSummary
10. Creating ML Models to Predict Sequences
Creating a Windowed DatasetCreating a Windowed Version of the Time Series DatasetCreating and Training a DNN to Fit the Sequence DataEvaluating the Results of the DNNTuning the Learning RateSummary
11. Using Convolutional and Recurrent Methods for Sequence Models
Convolutions for Sequence DataCoding ConvolutionsExperimenting with the Conv1D HyperparametersUsing NASA Weather DataReading GISS Data in PythonUsing RNNs for Sequence ModelingExploring a Larger DatasetUsing Other Recurrent MethodsUsing DropoutUsing Bidirectional RNNsSummary
12. Concepts of Inference
TensorsImage DataText DataTensors Out of a ModelSummary
13. Hosting PyTorch Models for Serving
Introducing TorchServeSetting Up TorchServePreparing Your EnvironmentSetting Up Your config.properties FileDefining Your ModelCreating the Handler FileCreating the Model ArchiveStarting the ServerTesting InferenceGoing FurtherServing with FlaskCreating an Environment for FlaskCreating a Flask Server in PythonSummary
14. Using Third-Party Models and Hubs
The Hugging Face HubUsing Hugging Face HubUsing a Model From Hugging Face HubPyTorch HubUsing PyTorch Vision ModelsNatural Language ProcessingOther ModelsSummary
15. Transformers and transformers
Understanding TransformersEncoder ArchitecturesThe Decoder ArchitectureThe Encoder-Decoder ArchitectureThe transformers APIGetting Started with transformersCore ConceptsPipelinesTokenizersSummary
16. Using LLMs with Custom Data
Fine-Tuning an LLMSetup and DependenciesLoading and Examining the DataInitializing the Model and TokenizerPreprocessing the DataCollating the DataDefining MetricsConfiguring TrainingInitializing the TrainerTraining and EvaluationSaving and Testing the ModelPrompt-Tuning an LLMPreparing the DataCreating the Data LoadersDefining the ModelTraining the ModelEvaluation During TrainingReporting Training MetricsSaving the Prompt EmbeddingsPerforming Inference with the ModelSummary
17. Serving LLMs with Ollama
Getting Started with OllamaRunning Ollama as a ServerBuilding an App that Uses an Ollama LLMThe ScenarioBuilding a Python Proof-of-ConceptCreating a Web App for OllamaThe app.js FileThe Index.html FileSummary
18. Introduction to RAG
What Is RAG?Getting Started with RAGUnderstanding SimilarityCreating the DatabasePerforming a Similarity SearchPutting It All TogetherUsing RAG Content with an LLMExtending to Hosted ModelsSummary
19. Using Generative Models with Hugging Face Diffusers
What Are Diffusion Models?Using Hugging Face DiffusersImage-to-Image with DiffusersInpainting with DiffusersSummary
20. Tuning Generative Image Models with LoRA and Diffusers
Training a LoRA with DiffusersGetting DiffusersGetting Data for Fine-Tuning a LoRAFine-Tuning a Model with DiffusersPublishing Your ModelGenerating an Image with the Custom LoRASummary
Index
About the Author

Overview

Eager to learn AI and machine learning but unsure where to start? Laurence Moroney's hands-on, code-first guide demystifies complex AI concepts without relying on advanced mathematics. Designed for programmers, it focuses on practical applications using PyTorch, helping you build real-world models without feeling overwhelmed.

From computer vision and natural language processing (NLP) to generative AI with Hugging Face Transformers, this book equips you with the skills most in demand for AI development today. You'll also learn how to deploy your models across the web and cloud confidently.

Gain the confidence to apply AI without needing advanced math or theory expertise
Discover how to build AI models for computer vision, NLP, and sequence modeling with PyTorch
Learn generative AI techniques with Hugging Face Diffusers and Transformers

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: 9781098199166Errata Page

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills