Machine Learning Deep Learning model deployment

Course Curriculum

Chapter 1: Introduction

Lecture 1: Introduction

Lecture 2: What is a Model?

Lecture 3: How do we create a Model?

Lecture 4: Types of Machine Learning

Chapter 2: Building, evaluating and saving a Model

Lecture 1: Creating a Spyder development environment

Lecture 2: Python NumPy Pandas Matplotlib crash course

Lecture 3: Building and evaluating a Classification Model

Lecture 4: Saving the Model and the Scaler

Chapter 3: Deploying the Model in other environments

Lecture 1: Predicting locally with deserialized Pickle objects

Lecture 2: Using the Model in Google Colab environment

Chapter 4: Creating a REST API for the Machine Learning Model

Lecture 1: Flask REST API Hello World

Lecture 2: Creating a REST API for the Model

Lecture 3: Signing up for a Google Cloud free trial

Lecture 4: Hosting the Machine Learning REST API on the Cloud

Lecture 5: Deleting the VM instance

Lecture 6: Serverless Machine Learning API using Cloud Functions

Lecture 7: Creating a REST API on Google Colab

Lecture 8: Postman REST client

Chapter 5: Deploying Deep Learning Models

Lecture 1: Understanding Deep Learning Neural Network

Lecture 2: Building and deploying PyTorch models

Lecture 3: Creating a REST API for the PyTorch Model

Lecture 4: Saving & loading TensorFlow Keras models

Lecture 5: Understanding Docker containers

Lecture 6: Creating a REST API using TensorFlow Model Server

Lecture 7: Converting a PyTorch model to TensorFlow format using ONNX

Chapter 6: Deploying NLP models for Twitter sentiment analysis

Lecture 1: Converting text to numeric values using bag-of-words model

Lecture 2: tf-idf model for converting text to numeric values

Lecture 3: Creating and saving text classifier and tf-idf models

Lecture 4: Creating a Twitter developer account

Lecture 5: Deploying tf-idf and text classifier models for Twitter sentiment analysis

Lecture 6: Creating a text classifier using PyTorch

Lecture 7: Creating a REST API for the PyTorch NLP model

Lecture 8: Twitter sentiment analysis with PyTorch REST API

Lecture 9: Creating a text classifier using TensorFlow

Lecture 10: Creating a REST API for TensforFlow models using Flask

Lecture 11: Serving TensorFlow models serverless

Lecture 12: Serving PyTorch models serverless

Chapter 7: Deploying models on browser using JavaScript and TensorFlow.js

Lecture 1: TensorFlow.js introduction

Lecture 2: Installing Visual Studio Code and Live Server

Lecture 3: JavaScript crash course (optional)

Lecture 4: Adding TensforFlow.js to a web page

Lecture 5: Basic tensor operations using TensorFlow.js

Lecture 6: Deploying Keras model on a web page using TensorFlow.js

Chapter 8: Model as a mathematical formula & Model as code

Lecture 1: Deriving formula from a Linear Regression Model

Lecture 2: Model as code

Chapter 9: Models in Database

Lecture 1: Storing and retrieving models from a database using Colab, Postgres and psycopg2

Lecture 2: Creating a local model store with PostgreSQL

Chapter 10: MLOps and MLflow

Lecture 1: Machine Learning Operations (MLOps)

Lecture 2: MLflow Introduction

Lecture 3: MLflow tracking concepts

Lecture 4: Installing MLflow on Windows and Mac

Lecture 5: Tracking Model training experiments with MLfLow

Lecture 6: MLflow auto-logging

Lecture 7: MLflow REST APIs

Lecture 8: Running MLflow on Colab

Lecture 9: Running MLFlow on Databricks

Lecture 10: Tracking PyTorch experiments with MLflow

Lecture 11: Deploying Models with MLflow

Lecture 12: Congratulations and Thank You

Chapter 11: Appendix – Generative AI – Miscellaneous Topics.

Lecture 1: OpenAI and the history of GPT models

Lecture 2: Creating an OpenAI account and invoking a text-to-speech model from Python code

Lecture 3: Invoking OpenAI Text Generation, Image Generation models from Python code

Lecture 4: Creating a Chatbot with OpenAI API and ChatGPT Model using Python

Lecture 5: Unlocking the Power of ChatGPT with prompt engineering