Development
Data Science
Docker
Deploy Machine Learning & NLP Models with Dockers (DevOps)
4.3 (628 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
3,515 students enrolled

Deploy Machine Learning & NLP Models with Dockers (DevOps)

Learn to build Machine Learning, Deep Learning & NLP Models & Deploy them with Docker Containers (DevOps) (in Python)
4.3 (628 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
3,515 students enrolled
Created by UNP United Network of Professionals
Last updated 6/2018
English
English [Auto]
Preview this course
Deploy Machine Learning & NLP Models with Dockers (DevOps)
Current price: $34.99 Original price: $49.99 Discount: 30% off
5 hours left at this price!
Buy now
30-Day Money-Back Guarantee
This course includes
  • 4 hours on-demand video
  • 10 downloadable resources
  • Full lifetime access
  • Access on mobile and TV
  • Assignments
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • How to synchronize the versatility of DevOps & Machine Learning
  • Master Docker , Docker Files, Docker Applications & Docker Containers (DevOps)
  • Flask Basics & Application Program Interface (API)
  • Build & Deploy a Random Forest Model
  • Build a Text based (Natural Language Processing : NLP ) CLUSTERING (KMeans) Model and expose it as an API
  • Build an API which will run a Deep Learning Model (Convolutional Neural Network : CNN) Model for Image Recognition & Classification
Course content
Expand all 54 lectures 04:12:38
+ – Flask basics
6 lectures 20:10
Introduction
Preview 00:38
Setting up a Flask Project
01:39
Simple Flask API to add two numbers
04:25
Taking user input with GET requests
04:13
POST request with Flask
05:49
Using Flask in the context of Machine Learning
03:26
+ – Exposing a Random Forest Machine Learning service as an API
9 lectures 37:39
Introduction
Preview 00:38
API & Dataset Overview
01:05
Training the Random Forest model
05:29
Pickling the Random Forest model
02:39
Exposing the Random Forest model as a Flask API
05:48
Testing the API model
04:24
Providing file input to Flask API
07:25
Flasgger for autogenerating UI
08:33
Summary
Preview 01:38
+ – Writing and building the Dockerfile
8 lectures 39:53
Introduction
Preview 00:46
Base Image & FROM command
03:26
COPY and EXPOSE commands
03:30
WORKDIR, RUN and CMD commands
04:08
Preparing the flask scripts for dockerizing
02:03
Writing the Dockerfile
08:35
Building the docker image
08:33
Running the Random Forest model on Docker
08:52
+ – Building a production grade Docker application
5 lectures 34:27
Introduction
Preview 04:43
Overall Architecture
04:21
Configuring the WSGI file
08:05
Writing a production grade Dockerfile
07:05
Running and debugging a docker container in production
10:13
Docker Quiz 1 – Basic Concepts, Commands
10 questions
+ – Building NLP based Text Clustering application
9 lectures 01:02:59
Introduction
Preview 02:07
Stemming & Lemmatization for cleaner text
10:34
Converting unstructured to structured data
09:44
KMeans Clustering
08:34
Preparing the excel output
10:01
Making the output Downloadable
06:18
Finding top keywords for kmeans clusters
07:09
Final output with charts
07:05
Summary
Preview 01:27
as mentioned in the lecture, merely building the flask app is not the end of the road. Dockerizing the application, i.e. writing a dockerfile and being efficient with docker build and docker run are essential as well
Dockerizing the text clustering app
2 questions
+ – API for image recognition with deep learning
8 lectures 45:21
Introduction
Preview 00:48
Visualizing the input images
07:14
Preparing the input images
09:20
Building the deep learning model
10:31
Training and saving the trained deep learning model
03:01
Generating test images
04:08
Flask API wrapper for making predictions
08:09
Summary
Preview 02:10
as mentioned in the lecture, merely building the flask app is not the end of the road. Dockerizing the application, i.e. writing a dockerfile and being efficient with docker build and docker run are essential as well
Dockerizing the deep learning app
2 questions
Requirements
  • Basic programming in any language
  • Basic Mathematics
  • Some exposure to Python (but not mandatory)
Description

Machine Learning, as we know it is the new buzz word in the industry today. This is practiced in every sector of business imaginable to provide data-driven solutions to complex business problems. This poses the challenge of deploying the solution, built by the Machine Learning technique so that it can be used across the intended Business Unit and not operated in silos.

This is an extensive and well-thought course created & designed by UNP's elite team of Data Scientists from around the world to focus on the challenges that are being faced by Data Scientists and Computational Solution Architects across the industry  which is summarized the below  sentence :

"I HAVE THE MACHINE LEARNING MODEL, IT IS WORKING AS EXPECTED !! NOW, WHAT ?????" 

This course will help you create a solid foundation of the essential topics of data science along with a solid foundation of deploying those created solutions through Docker containers which eventually will expose your model as a service (API) which can be used by all who wish for it.

At the end of this course, you will be able to:

  • Learn about Docker, Docker Files, Docker Containers

  • Learn Flask Basics & Application Program Interface (API)

  • Build a Random Forest Model and deploy it.

  • Build a Natural Language Processing based Test Clustering Model (K-Means) and visualize it.

  • Build an API for Image Processing and Recognition with a Deep Learning Model under the hood (Convolutional Neural Network: CNN)

 This course is a perfect blend of foundations of data science, industry standards, broader understanding of machine learning and practical applications and most importantly deploying them.

Who this course is for:
  • Anyone willing to venture into the realm of data science
  • Anyone who would be interested in deploying a Data Science Solution, can be Regression, NLP or even Deep Learning Models
Featured review
Bala Deshpande
Bala Deshpande ( 92 courses, 26 reviews )
a year ago
The instructor has put together a very handy and practical guide that combines modeling and dev-ops in one succinct course. It is ideal for a working professional who wants to get the low-down at a rapid but hands on pace. Excellent material!