Deploy Machine Learning Models to Production: With Flask, Streamlit, Docker, and Kubernetes on Google Cloud Platform (Paperback)

Chapter goal: This chapter covers the steps right from reading the data, pre-processing, feature engineering, model training and prediction on local as well as on the cloud. This chapter provides the audience with a set of required libraries and code/data download information so that the user can set up their environment appropriately.

Sub -Topics

? Configuring your development environment

? Installing required libraries

? Building Python and TensorFlow based models

Chapter 2: Introduction to Model Deployment and Challenges

No of pages: 20

Sub - Topics

? Understanding model deployment

? Understanding challenges

? Serverless architecture for deployment

Chapter 3: Model Deployment Using Flask

No of pages: 25

Chapter goal: This chapter covers the lightweight web framework ? Flask for deploying the small and simple machine learning models.

Sub - Topics:

? What is Flask

? Build Python-based model

? Deploy machine learning model using Flask

Chapter 4: Model Containerization Using Docker

No of pages:30

Chapter goal: This chapter is devoted to the understanding of docker platform. It covers all the steps to containerize any model, application using docker.

Sub - Topics:

? Introduction to Docker

? Build a custom Docker image

? Run a machine Learning model using Docker

Chapter 5: Introduction to Kubeflow

No of pages:30

Chapter goal: This chapter serves as an introduction to our core theme of the book: Build and deploy machine learning models using Kubeflow. The chapter begins with covering various components of Kubeflow and offers information on its advantages over other platforms

Sub - Topics:

? Gentle Introduction to Kubernetes

? Introduction to Kubeflow

? Kubeflow components

Chapter 6: Model Deployment Using Kubeflow

No of pages: 35

Chapter goal: This chapter focuses on the industrial implementation of deep learning model in the Google Cloud Platform using Kubeflow. This chapter also demonstrates various techniques like hyperparameter tuning and workflows for training and serving the models for predictions

Sub - Topics:

? Google Cloud Platform configuration

? Hyperparameter tuning of the model

? Training and serving model at scale

Chapter 7: Model Deployment Using MLflow

No of pages:20

Chapter goal: This chapter covers the alternative to Google’s Kubeflow ? Spark’s MLflow. It showcases the process of serializing the machine learning model and serving it for predictions using MLflow.

Sub - Topics:

? Deep learning using MLflow

? Model management using MLflow

? Model serving using MLflow

Pramod Singh (지은이)    정보 더보기

분야의 베스트셀러 >