Deploying AI & Machine Learning Models for Business | Python

Course Curriculum

Chapter 1: Course Overview

Lecture 1: Introduction

Lecture 2: I have a model. Now what?

Lecture 3: Skills Checklist

Lecture 4: Learning Goals

Chapter 2: Docker basics

Lecture 1: Why docker?

Lecture 2: What are docker containers?

Lecture 3: Importance of docker containers in machine learning

Lecture 4: Where devops meets data science

Lecture 5: Summary

Chapter 3: Flask basics

Lecture 1: Introduction

Lecture 2: Setting up a Flask Project

Lecture 3: Simple Flask API to add two numbers

Lecture 4: Taking user input with GET requests

Lecture 5: POST request with Flask

Lecture 6: Using Flask in the context of Machine Learning

Chapter 4: Exposing a Random Forest Machine Learning service as an API

Lecture 1: Introduction

Lecture 2: API & Dataset Overview

Lecture 3: Training the Random Forest model

Lecture 4: Pickling the Random Forest model

Lecture 5: Exposing the Random Forest model as a Flask API

Lecture 6: Testing the API model

Lecture 7: Providing file input to Flask API

Lecture 8: Flasgger for autogenerating UI

Lecture 9: Summary

Chapter 5: Writing and building the Dockerfile

Lecture 1: Introduction

Lecture 2: Base Image & FROM command

Lecture 3: COPY and EXPOSE commands

Lecture 4: WORKDIR, RUN and CMD commands

Lecture 5: Preparing the flask scripts for dockerizing

Lecture 6: Writing the Dockerfile

Lecture 7: Building the docker image

Lecture 8: Running the Random Forest model on Docker

Chapter 6: Building a production grade Docker application

Lecture 1: Introduction

Lecture 2: Overall Architecture

Lecture 3: Configuring the WSGI file

Lecture 4: Writing a production grade Dockerfile

Lecture 5: Running and debugging a docker container in production

Chapter 7: Building NLP based Text Clustering application

Lecture 1: Introduction

Lecture 2: Stemming & Lemmatization for cleaner text

Lecture 3: Converting unstructured to structured data

Lecture 4: KMeans Clustering

Lecture 5: Preparing the excel output

Lecture 6: Making the output Downloadable

Lecture 7: Finding top keywords for kmeans clusters

Lecture 8: Final output with charts

Lecture 9: Summary

Chapter 8: API for image recognition with deep learning

Lecture 1: Introduction

Lecture 2: Visualizing the input images

Lecture 3: Preparing the input images

Lecture 4: Building the deep learning model

Lecture 5: Training and saving the trained deep learning model

Lecture 6: Generating test images

Lecture 7: Flask API wrapper for making predictions

Lecture 8: Summary