PyTorch - Bert Gollnick

. .

Résumé :

... Preface ... 15

... Target Group ... 15

... Requirements ... 15

... Structure of the Book ... 16

... How to Use This Book ... 18

... Downloading Code and Additional Materials ... 18

... Preparing the System ... 19

... Acknowledgements ... 24

... Conventions Used in This Book ... 25

1 ... Introduction to Deep Learning ... 27

1.1 ... What is Deep Learning? ... 27

1.2 ... What Can You Use Deep Learning For? ... 28

1.3 ... How Does Deep Learning Work? ... 31

1.4 ... Historical Development ... 33

1.5 ... Perceptrons ... 34

1.6 ... Network Structure and Layers ... 34

1.7 ... Activation Functions ... 35

1.8 ... Loss Functions ... 38

1.9 ... Optimizers and Updating Parameters ... 40

1.10 ... Tensor Handling ... 42

1.11 ... Summary ... 50

2 ... Creating Your First PyTorch Model ... 51

2.1 ... Data Preparation ... 51

2.2 ... Model Creation ... 60

2.3 ... The Model Class and the Optimizer ... 68

2.4 ... Batches ... 72

2.5 ... Coding: Implementation of Dataset and DataLoader ... 76

2.6 ... Loading and Saving a Model ... 80

2.7 ... Data Sampling ... 83

2.8 ... Summary ... 92

3 ... Classification Models ... 93

3.1 ... Classification Types ... 93

3.2 ... Confusion Matrix ... 95

3.3 ... Receiver Operator Characteristic Curve ... 97

3.4 ... Coding: Binary Classification ... 99

3.5 ... Coding: Multiclass Classification ... 112

3.6 ... Summary ... 124

4 ... Computer Vision ... 127

4.1 ... How Do Models Handle Images? ... 128

4.2 ... Network Architecture ... 129

4.3 ... Coding: Image Classification ... 134

4.4 ... Object Detection ... 163

4.5 ... Semantic Segmentation ... 178

4.6 ... Style Transfer ... 188

4.7 ... Summary ... 197

5 ... Recommendation Systems ... 199

5.1 ... Theoretical Foundations ... 199

5.2 ... Coding: Recommendation Systems ... 202

5.3 ... Summary ... 218

6 ... Autoencoders ... 219

6.1 ... Architecture ... 220

6.2 ... Coding: Autoencoder ... 220

6.3 ... Variational Autoencoders ... 230

6.4 ... Coding: Variational Autoencoder ... 231

6.5 ... Summary ... 240

7 ... Graph Neural Networks ... 241

7.1 ... Introduction to Graph Theory ... 241

7.2 ... Coding: Developing a Graph ... 246

7.3 ... Coding: Training a Graph Neural Network ... 250

7.4 ... Summary ... 259

8 ... Time Series Forecasting ... 261

8.1 ... Modeling Approaches ... 261

8.2 ... Coding: Custom Model ... 266

8.3 ... Coding: Using PyTorch Forecasting ... 280

8.4 ... Summary ... 288

9 ... Language Models ... 289

9.1 ... Using Large Language Models with Python ... 290

9.2 ... Model Parameters ... 304

9.3 ... Model Selection ... 307

9.4 ... Message Types ... 310

9.5 ... Prompt Templates ... 311

9.6 ... Chains ... 315

9.7 ... Structured Outputs ... 317

9.8 ... Deep Dive: How Do Transformers Work? ... 320

9.9 ... Summary ... 327

10 ... Pretrained Networks and Fine-Tuning ... 329

10.1 ... Pretrained Networks with Hugging Face ... 329

10.2 ... Transfer Learning ... 332

10.3 ... Coding: Fine-Tuning a Computer Vision Model ... 335

10.4 ... Coding: Fine-Tuning a Language Model ... 343

10.5 ... Sum...

Biographie:
Bert Gollnick is a senior data scientist, specializing in renewable energies. For many years, he has taught courses about data science and machine learning, and more recently, about generative AI and natural language processing. Bert studied aeronautics at the Technical University of Berlin and economics at the University of Hagen. His main areas of interest are machine learning and data science....

Sommaire:

PyTorch is the framework for deep learning-so dive on in! Learn how to train, optimize, and deploy AI models with PyTorch by following practical exercises and example code. You'll walk through using PyTorch for linear regression, classification, image processing, recommendation systems, autoencoders, graph neural networks, time series predictions, and language models-all the essentials. Then evaluate and deploy your models using key tools like MLflow, TensorBoard, and FastAPI. With information on fine-tuning your models using HuggingFace and reducing training time with PyTorch Lightning, this practical guide is the one you need!

Highlights:

1) Deep learning

2) Linear regression

3) Classification

4) Computer vision

5) Recommendation systems

6) Autoencoders

7) Graph neural networks (GNNs)

8) Time series predictions

9) Language models

10) Pretrained networks

11)Evaluation and deployment

12)PyTorch Lightning