Video description
In Video Editions the narrator reads the book while the content, figures, code listings, diagrams, and text appear on the screen. Like an audiobook that you can also watch as a video.
A vital guide to building the platforms and systems that bring deep learning models to production.
In Designing Deep Learning Systems you will learn how to:
- Transfer your software development skills to deep learning systems
- Recognize and solve common engineering challenges for deep learning systems
- Understand the deep learning development cycle
- Automate training for models in TensorFlow and PyTorch
- Optimize dataset management, training, model serving and hyperparameter tuning
- Pick the right open-source project for your platform
Deep learning systems are the components and infrastructure essential to supporting a deep learning model in a production environment. Written especially for software engineers with minimal knowledge of deep learning’s design requirements, Designing Deep Learning Systems is full of hands-on examples that will help you transfer your software development skills to creating these deep learning platforms. You’ll learn how to build automated and scalable services for core tasks like dataset management, model training/serving, and hyperparameter tuning. This book is the perfect way to step into an exciting—and lucrative—career as a deep learning engineer.
Designing Deep Learning Systems: A software engineer's guide teaches you everything you need to design and implement a production-ready deep learning platform. First, it presents the big picture of a deep learning system from the developer’s perspective, including its major components and how they are connected. Then, it carefully guides you through the engineering methods you’ll need to build your own maintainable, efficient, and scalable deep learning platforms.
Chi Wang is a principal software developer in the Salesforce Einstein group. Donald Szeto was the co-founder and CTO of PredictionIO.
Table of contents
- Chapter 1. An introduction to deep learning systems
- Chapter 1. Deep learning system design overview
- Chapter 1. Building a deep learning system vs. developing a model
- Chapter 1. Summary
- Chapter 2. Dataset management service
- Chapter 2. Touring a sample dataset management service
- Chapter 2. Open source approaches
- Chapter 2. Summary
- Chapter 3. Model training service
- Chapter 3. Deep learning training code pattern
- Chapter 3. A sample model training service
- Chapter 3. Kubeflow training operators: An open source approach
- Chapter 3. When to use the public cloud
- Chapter 3. Summary
- Chapter 4. Distributed training
- Chapter 4. Data parallelism
- Chapter 4. A sample service supporting data parallel–distributed training
- Chapter 4. Training large models that can’t load on one GPU
- Chapter 4. Summary
- Chapter 5. Hyperparameter optimization service
- Chapter 5. Understanding hyperparameter optimization
- Chapter 5. Designing an HPO service
- Chapter 5. Open source HPO libraries
- Chapter 5. Summary
- Chapter 6. Model serving design
- Chapter 6. Common model serving strategies
- Chapter 6. Designing a prediction service
- Chapter 6. Summary
- Chapter 7. Model serving in practice
- Chapter 7. TorchServe model server sample
- Chapter 7. Model server vs. model service
- Chapter 7. Touring open source model serving tools
- Chapter 7. Releasing models
- Chapter 7. Postproduction model monitoring
- Chapter 7. Summary
- Chapter 8. Metadata and artifact store
- Chapter 8. Metadata in a deep learning context
- Chapter 8. Designing a metadata and artifacts store
- Chapter 8. Open source solutions
- Chapter 8. Summary
- Chapter 9. Workflow orchestration
- Chapter 9. Designing a workflow orchestration system
- Chapter 9. Touring open source workflow orchestration systems
- Chapter 9. Summary
- Chapter 10. Path to production
- Chapter 10. Model productionization
- Chapter 10. Model deployment strategies
- Chapter 10. Summary
- Appendix A. A “hello world” deep learning system
- Appendix A. Lab demo
- Appendix B. Survey of existing solutions
- Appendix B. Google Vertex AI
- Appendix B. Microsoft Azure Machine Learning
- Appendix B. Kubeflow
- Appendix B. Side-by-side comparison
- Appendix C. Creating an HPO service with Kubeflow Katib
- Appendix C. Getting started with Katib
- Appendix C. Expedite HPO
- Appendix C. Katib system design
- Appendix C. Adding a new algorithm
- Appendix C. Further reading
- Appendix C. When to use it
Product information
- Title: Designing Deep Learning Systems, Video Edition
- Author(s):
- Release date: June 2023
- Publisher(s): Manning Publications
- ISBN: None
You might also like
article
Use GitHub Copilot: Additional Tips
Using GitHub Copilot can feel like magic. The tool automatically fills out entire blocks of code--but …
video
GenAI Essentials for Everyone - Overview
Our team of experts has hand-selected and organized the most crucial concepts and practical applications of …
book
Designing Deep Learning Systems
A vital guide to building the platforms and systems that bring deep learning models to production. …
article
Use Github Copilot for Prompt Engineering
Using GitHub Copilot can feel like magic. The tool automatically fills out entire blocks of code--but …