book

The TensorFlow Workshop

Name: The TensorFlow Workshop
ISBN: 9781800205253

by Matthew Moocarme, Abhranshu Bagchi, Anthony So, Anthony Maddalone

December 2021

Beginner to intermediate

600 pages

11h 3m

English

Packt Publishing

Read now

Unlock full access

The TensorFlow Workshop
Preface
About the BookAbout the AuthorsWho This Book Is ForAbout the ChaptersConventionsCode PresentationMinimum Hardware RequirementsDownloading the Code BundleSetting Up Your EnvironmentInstalling Anaconda on Your SystemLaunching Jupyter NotebookInstalling the tensorflow Virtual EnvironmentGet in TouchPlease Leave a Review
1. Introduction to Machine Learning with TensorFlow
IntroductionImplementing Artificial Neural Networks in TensorFlowAdvantages of TensorFlowDisadvantages of TensorFlowThe TensorFlow Library in PythonExercise 1.01: Verifying Your Version of TensorFlowIntroduction to TensorsScalars, Vectors, Matrices, and TensorsExercise 1.02: Creating Scalars, Vectors, Matrices, and Tensors in TensorFlowTensor AdditionExercise 1.03: Performing Tensor Addition in TensorFlowActivity 1.01: Performing Tensor Addition in TensorFlowReshapingTensor TranspositionExercise 1.04: Performing Tensor Reshaping and Transposition in TensorFlowActivity 1.02: Performing Tensor Reshaping and Transposition in TensorFlowTensor MultiplicationExercise 1.05: Performing Tensor Multiplication in TensorFlowOptimizationForward PropagationBackpropagationLearning Optimal ParametersOptimizers in TensorFlowActivation functionsActivity 1.03: Applying Activation Functions Summary
2. Loading and Processing Data
IntroductionExploring Data TypesData PreprocessingProcessing Tabular DataExercise 2.01: Loading Tabular Data and Rescaling Numerical FieldsActivity 2.01: Loading Tabular Data and Rescaling Numerical Fields with a MinMax ScalerExercise 2.02: Preprocessing Non-Numerical DataProcessing Image DataExercise 2.03: Loading Image Data for Batch ProcessingImage AugmentationActivity 2.02: Loading Image Data for Batch ProcessingText ProcessingExercise 2.04: Loading Text Data for TensorFlow ModelsAudio ProcessingExercise 2.05: Loading Audio Data for TensorFlow ModelsActivity 2.03: Loading Audio Data for Batch ProcessingSummary
3. TensorFlow Development
IntroductionTensorBoardExercise 3.01: Using TensorBoard to Visualize Matrix Multiplication Activity 3.01: Using TensorBoard to Visualize Tensor TransformationsExercise 3.02: Using TensorBoard to Visualize Image BatchesTensorFlow HubExercise 3.03: Downloading a Model from TensorFlow Hub Google ColabAdvantages of Google ColabDisadvantages of Google ColabDevelopment on Google ColabExercise 3.04: Using Google Colab to Visualize DataActivity 3.02: Performing Word Embedding from a Pre-Trained Model from TensorFlow HubSummary
4. Regression and Classification Models
IntroductionSequential ModelsKeras LayersExercise 4.01: Creating an ANN with TensorFlowModel FittingThe Loss FunctionModel EvaluationExercise 4.02: Creating a Linear Regression Model as an ANN with TensorFlowExercise 4.03: Creating a Multi-Layer ANN with TensorFlowActivity 4.01: Creating a Multi-Layer ANN with TensorFlowClassification ModelsExercise 4.04: Creating a Logistic Regression Model as an ANN with TensorFlowActivity 4.02: Creating a Multi-Layer Classification ANN with TensorFlowSummary
5. Classification Models
IntroductionBinary Classification Logistic RegressionBinary Cross-EntropyBinary Classification ArchitectureExercise 5.01: Building a Logistic Regression ModelMetrics for ClassifiersAccuracy and Null AccuracyPrecision, Recall, and the F1 ScoreConfusion MatricesExercise 5.02: Classification Evaluation MetricsMulti-Class ClassificationThe Softmax FunctionCategorical Cross-EntropyMulti-Class Classification ArchitectureExercise 5.03: Building a Multi-Class ModelActivity 5.01: Building a Character Recognition Model with TensorFlowMulti-Label Classification Activity 5.02: Building a Movie Genre Tagging a Model with TensorFlowSummary
6. Regularization and Hyperparameter Tuning
IntroductionRegularization Techniques L1 RegularizationL2 RegularizationExercise 6.01: Predicting a Connect-4 Game Outcome Using the L2 RegularizerDropout RegularizationExercise 6.02: Predicting a Connect-4 Game Outcome Using DropoutEarly StoppingActivity 6.01: Predicting Income with L1 and L2 RegularizersHyperparameter TuningKeras Tuner Random SearchExercise 6.03: Predicting a Connect-4 Game Outcome Using Random Search from Keras Tuner HyperbandExercise 6.04: Predicting a Connect-4 Game Outcome Using Hyperband from Keras Tuner Bayesian OptimizationActivity 6.02: Predicting Income with Bayesian Optimization from Keras TunerSummary
7. Convolutional Neural Networks
IntroductionCNNsImage RepresentationThe Convolutional LayerCreating the ModelExercise 7.01: Creating the First Layer to Build a CNNPooling LayerMax PoolingAverage PoolingExercise 7.02: Creating a Pooling Layer for a CNNFlattening LayerExercise 7.03: Building a CNNImage AugmentationBatch NormalizationExercise 7.04: Building a CNN with Additional Convolutional LayersBinary Image ClassificationObject ClassificationExercise 7.05: Building a CNNActivity 7.01: Building a CNN with More ANN LayersSummary
8. Pre-Trained Networks
IntroductionImageNetTransfer LearningExercise 8.01: Classifying Cats and Dogs with Transfer LearningFine-TuningActivity 8.01: Fruit Classification with Fine-TuningTensorFlow HubFeature ExtractionActivity 8.02: Transfer Learning with TensorFlow HubSummary

9. Recurrent Neural Networks
IntroductionSequential DataExamples of Sequential DataExercise 9.01: Training an ANN for Sequential Data – Nvidia Stock PredictionRecurrent Neural NetworksRNN ArchitectureVanishing Gradient ProblemLong Short-Term Memory NetworkExercise 9.02: Building an RNN with an LSTM Layer – Nvidia Stock PredictionActivity 9.01: Building an RNN with Multiple LSTM Layers to Predict Power ConsumptionNatural Language ProcessingData PreprocessingDataset CleaningGenerating a Sequence and TokenizationPadding SequencesBack Propagation Through Time (BPTT)Exercise 9.03: Building an RNN with an LSTM Layer for Natural Language ProcessingActivity 9.02: Building an RNN for Predicting Tweets' SentimentSummary
10. Custom TensorFlow Components
IntroductionTensorFlow APIsImplementing Custom Loss FunctionsBuilding a Custom Loss Function with the Functional APIBuilding a Custom Loss Function with the Subclassing APIExercise 10.01: Building a Custom Loss FunctionImplementing Custom LayersIntroduction to ResNet BlocksBuilding Custom Layers with the Functional APIBuilding Custom Layers with SubclassingExercise 10.02: Building a Custom LayerActivity 10.01: Building a Model with Custom Layers and a Custom Loss FunctionSummary
11. Generative Models
IntroductionText GenerationExtending NLP Sequence Models to Generate TextDataset CleaningGenerating a Sequence and TokenizationGenerating a Sequence of n-gram TokensPadding SequencesExercise 11.01: Generating Text Generative Adversarial Networks The Generator Network The Discriminator NetworkThe Adversarial NetworkCombining the Generative and Discriminative ModelsGenerating Real Samples with Class LabelsCreating Latent Points for the GeneratorUsing the Generator to Generate Fake Samples and Class LabelsEvaluating the Discriminator ModelTraining the Generator and DiscriminatorCreating the Latent Space, Generator, Discriminator, GAN, and Training DataExercise 11.02: Generating Sequences with GANs Deep Convolutional Generative Adversarial Networks (DCGANs)Training a DCGANExercise 11.03: Generating Images with DCGAN Activity 11.01: Generating Images Using GANsSummary
Appendix
1. Introduction to Machine Learning with TensorFlowActivity 1.01: Performing Tensor Addition in TensorFlowActivity 1.02: Performing Tensor Reshaping and Transposition in TensorFlowActivity 1.03: Applying Activation Functions 2. Loading and Processing DataActivity 2.01: Loading Tabular Data and Rescaling Numerical Fields with a MinMax ScalerActivity 2.02: Loading Image Data for Batch ProcessingActivity 2.03: Loading Audio Data for Batch Processing3. TensorFlow DevelopmentActivity 3.01: Using TensorBoard to Visualize Tensor TransformationsActivity 3.02: Performing Word Embedding from a Pre-Trained Model from TensorFlow Hub4. Regression and Classification ModelsActivity 4.01: Creating a Multi-Layer ANN with TensorFlowActivity 4.02: Creating a Multi-Layer Classification ANN with TensorFlow5. Classification ModelsActivity 5.01: Building a Character Recognition Model with TensorFlowActivity 5.02: Building a Movie Genre Tagging a Model with TensorFlow6. Regularization and Hyperparameter TuningActivity 6.01: Predicting Income with L1 and L2 RegularizersActivity 6.02: Predicting Income with Bayesian Optimization from Keras Tuner7. Convolutional Neural NetworksActivity 7.01: Building a CNN with More ANN Layers8. Pre-Trained NetworksActivity 8.01: Fruit Classification with Fine-TuningActivity 8.02: Transfer Learning with TensorFlow Hub9. Recurrent Neural NetworksActivity 9.01: Building an RNN with Multiple LSTM Layers to Predict Power ConsumptionActivity 9.02: Building an RNN for Predicting Tweets' Sentiment10. Custom TensorFlow ComponentsActivity 10.01: Building a Model with Custom Layers and a Custom Loss Function11. Generative ModelsActivity 11.01: Generating Images Using GANs
Hey!

Overview

The TensorFlow Workshop introduces you to building deep learning models using TensorFlow, emphasizing hands-on experience with real datasets. You'll learn to process data, construct models, and utilize TensorFlow tools through practical exercises that mimic real-world scenarios.

What this Book will help me do

Understand tensor operations and their applications in deep learning.
Preprocess and work with datasets of different formats including image and sequential data.
Learn to utilize a variety of deep learning layers, their functions, and integration into models.
Gain expertise in hyperparameter tuning for improved model performance.
Leverage pre-trained models to enhance development efficiency and explore generative modeling.

Author(s)

The authors Matthew Moocarme, Abhranshu Bagchi, Anthony So None, and None Maddalone bring extensive experience in machine learning, TensorFlow applications, and technical education. Their collaborative expertise ensures a blend of theoretical and practical knowledge, making TensorFlow concepts approachable and applicable.

Who is it for?

This book is perfect for aspiring data scientists and machine learning enthusiasts with a beginner to intermediate understanding of Python and machine learning principles. Ideal readers seek to delve into TensorFlow to enhance their data science projects and advance their skills in deep learning. Practical experience is woven throughout to aid immediate application.

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: 9781800205253

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills