Deploy machine learning models to production : with Flask, Streamlit, Docker, and Kubernetes on Google Cloud Platform /

Build and deploy machine learning and deep learning models in production with end-to-end examples. This book begins with a focus on the machine learning model deployment process and its related challenges. Next, it covers the process of building and deploying machine learning models using different...

Descripción completa

Detalles Bibliográficos
Clasificación:Libro Electrónico
Autor principal: Singh, Pramod
Formato: Electrónico eBook
Idioma:Inglés
Publicado: Berkeley, CA : Apress L.P., 2021.
Temas:
Machine learning.
Python (Computer program language)
Open source software.
Computer programming.
Apprentissage automatique.
Python (Langage de programmation)
Logiciels libres.
Programmation (Informatique)
computer programming.
Computer programming
Machine learning
Open source software
Acceso en línea:Texto completo (Requiere registro previo con correo institucional)
Tabla de Contenidos:
  • Intro
  • Table of Contents
  • About the Author
  • About the Technical Reviewer
  • Acknowledgments
  • Introduction
  • Chapter 1: Introduction to Machine Learning
  • History
  • The Last Decade
  • Rise in Data
  • Increased Computational Efficiency
  • Improved ML Algorithms
  • Availability of Data Scientists
  • Machine Learning
  • Supervised Machine Learning
  • Unsupervised Learning
  • Semi-supervised Learning
  • Reinforcement Learning
  • Gradient Descent
  • Bias vs. Variance
  • Cross Validation and Hyperparameters
  • Performance Metrics
  • Deep Learning
  • Human Brain Neuron vs. Artificial Neuron
  • Activation Functions
  • Sigmoid Activation Function
  • Hyperbolic Tangent
  • Rectified Linear Unit
  • Neuron Computation Example
  • Neural Network
  • Training Process
  • Role of Bias in Neural Networks
  • CNN
  • RNN
  • Industrial Applications and Challenges
  • Retail
  • Healthcare
  • Finance
  • Travel and Hospitality
  • Media and Marketing
  • Manufacturing and Automobile
  • Social Media
  • Others
  • Challenges
  • Requirements
  • Conclusion
  • Chapter 2: Model Deployment and Challenges
  • Model Deployment
  • Why Do We Need Machine Learning Deployment?
  • Challenges
  • Challenge 1: Coordination Between Stakeholders
  • Challenge 2: Programming Language Discrepancy
  • Challenge 3: Model Drift
  • Changing Behavior of the Data
  • Changing Interpretation of the New Data
  • Challenge 4: On-Prem vs. Cloud-Based Deployment
  • Challenge 5: Clear Ownership
  • Challenge 6: Model Performance Monitoring
  • Challenge 7: Release/Version Management
  • Challenge 8: Privacy Preserving and Secure Model
  • Conclusion
  • Chapter 3: Machine Learning Deployment as a Web Service
  • Introduction to Flask
  • route Function
  • run Method
  • Deploying a Machine Learning Model as a REST Service
  • Templates
  • Deploying a Machine Learning Model Using Streamlit
  • Deploying a Deep Learning Model
  • Training the LSTM Model
  • Conclusion
  • Chapter 4: Machine Learning Deployment Using Docker
  • What Is Docker, and Why Do We Need It?
  • Introduction to Docker
  • Docker vs. Virtual Machines
  • Docker Components and Useful Commands
  • Docker Image
  • Dockerfile
  • Dockerfile Commands
  • Docker Hub
  • Docker Client and Docker Server
  • Docker Container
  • Some Useful Container-Related Commands
  • Machine Learning Using Docker
  • Step 1: Training the Machine Learning Model
  • Step 2: Exporting the Trained Model
  • Step 3: Creating a Flask App Including UI
  • Step 4: Building the Docker Image
  • Step 5: Running the Docker Container
  • Step 6: Stopping/Killing the Running Container
  • Conclusion
  • Chapter 5: Machine Learning Deployment Using Kubernetes
  • Kubernetes Architecture
  • Kubernetes Master
  • Worker Nodes
  • ML App Using Kubernetes
  • Google Cloud Platform
  • Conclusion
  • Index

Ejemplares similares