book

PyTorch Pocket Reference

by Joe Papa

May 2021

Intermediate to advanced

307 pages

6h 1m

English

O'Reilly Media, Inc.

Book available

Read now

Unlock full access

Who Should Read This BookWhy I Wrote This BookNavigating This BookConventions Used in This BookUsing Code ExamplesO’Reilly Online LearningHow to Contact UsAcknowledgments
What Is PyTorch?Why Use PyTorch?Getting StartedRunning in Google ColaboratoryRunning on a Local ComputerRunning on Cloud PlatformsVerifying Your PyTorch EnvironmentA Fun Example
What Is a Tensor?Simple CPU ExampleSimple GPU ExampleMoving Tensors Between CPUs and GPUsCreating TensorsTensor AttributesData TypesCreating Tensors from Random SamplesCreating Tensors Like Other TensorsTensor OperationsIndexing, Slicing, Combining, and Splitting TensorsTensor Operations for MathematicsAutomatic Differentiation (Autograd)
The Overall ProcessData PreparationData LoadingData TransformsData BatchingGeneral Data Preparation (torch.utils.data)Model DevelopmentModel DesignTrainingValidationTestingModel DeploymentSaving ModelsDeploying to PyTorch HubDeploying to Production
Image Classification with Transfer LearningData ProcessingModel DesignTraining and ValidationTesting and DeploymentSentiment Analysis with TorchtextData ProcessingModel DesignTraining and ValidationTesting and DeploymentGenerative Learning—Generating Fashion-MNIST Images with DCGANData ProcessingModel DesignTrainingTesting and Deployment
Custom Layers and ActivationsCustom Layer Example (Complex Linear)Custom Activation Example (Complex ReLU)Custom Model ArchitecturesCustom Loss FunctionsCustom Optimizer AlgorithmsCustom Training, Validation, and Test Loops
PyTorch on a TPUPyTorch on Multiple GPUs (Single Machine)Data Parallel ProcessingModel Parallel ProcessingCombined Data Parallel Processing and Model Parallel ProcessingDistributed Training (Multiple Machines)Model OptimizationHyperparameter TuningQuantizationPruning
PyTorch Deployment Tools and LibrariesCommon Example ModelPython APITorchScriptTorchServeONNXMobile LibrariesDeploying to a Flask AppColab Flask AppDeploying to the Cloud with TorchServeQuick Start with DockerDeploying to Mobile and EdgeiOSAndroidOther Edge Devices
The PyTorch EcosystemTorchvision for Image and VideoDatasets and I/OModelsTransforms, Operations, and UtilitiesTorchtext for NLPCreate a Dataset ObjectPreprocess DataCreate a Dataloader for BatchingData (torchtext.data)Datasets (torchtext.datasets)Vocabularies (torchtext.vocab)TensorBoard for VisualizationLearning Curves with SCALARSModel Architectures with GRAPHSData with IMAGES, TEXT, and PROJECTORWeight Distributions with DISTRIBUTIONS and HISTOGRAMSHyperparameters with HPARAMSThe TensorBoard APIPapers with CodeAdditional PyTorch ResourcesTutorialsBooksOnline Courses and Live Training

Overview

This concise, easy-to-use reference puts one of the most popular frameworks for deep learning research and development at your fingertips. Author Joe Papa provides instant access to syntax, design patterns, and code examples to accelerate your development and reduce the time you spend searching for answers.

Research scientists, machine learning engineers, and software developers will find clear, structured PyTorch code that covers every step of neural network development-from loading data to customizing training loops to model optimization and GPU/TPU acceleration. Quickly learn how to deploy your code to production using AWS, Google Cloud, or Azure and deploy your ML models to mobile and edge devices.