samcx.com
4.51 out of 5
4.51
196 reviews on Udemy

Deployment of Machine Learning Models in Production | Python

Deploy ML Model with BERT, DistilBERT, FastText NLP Models in Production with Flask, uWSGI, and NGINX at AWS EC2
Instructor:
Laxmi Kant
3,860 students enrolled
English [Auto]
Complete End to End NLP Application
How to work with BERT in Google Colab
How to use BERT for Text Classification
Deploy Production Ready ML Model
Fine Tune and Deploy ML Model with Flask
Deploy ML Model in Production at AWS
Deploy ML Model at Ubuntu and Windows Server
DistilBERT vs BERT
Optimize your NLP Code
You will learn how to develop and deploy FastText model on AWS
Learn Multi-Label and Multi-Class classification in NLP

Are you ready to kickstart your  Advanced NLP course? Are you ready to deploy your machine learning models in production at AWS? You will learn each and every steps on how to build and deploy your ML model on a robust and secure server at AWS.

Prior knowledge of python and Data Science is assumed. If you are AN absolute beginner in Data Science, please do not take this course. This course is made for medium or advanced level of Data Scientist.

You should have an introductory knowledge of Python, Machine Learning, and Natural Language Processing before enrolling in this course otherwise please do not enroll in this course. This is an advanced NLP course.

What is BERT?

BERT is a method of pre-training language representations, meaning that we train a general-purpose “language understanding” model on a large text corpus (like Wikipedia), and then use that model for downstream NLP tasks that we care about (like question answering). BERT outperforms previous methods because it is the first unsupervised, deeply bidirectional system for pre-training NLP.

Unsupervised means that BERT was trained using only a plain text corpus, which is important because an enormous amount of plain text data is publicly available on the web in many languages.

Why is BERT so revolutionary?

Not only is it a framework that has been pre-trained with the biggest data set ever used, but it is also remarkably easy to adapt to different NLP applications, by adding additional output layers. This allows users to create sophisticated and precise models to carry out a wide variety of NLP tasks.

Here is what you will learn in this course

  • Notebook Setup and What is BERT.

  • Data Preprocessing.

  • BERT Model Building and Training.

  • BERT Model Evaluation and Saving.

  • DistilBERT Model Fine Tuning and Deployment

  • Deploy Your ML Model at AWS with Flask Server

  • Deploy Your Model at Both Windows and Ubuntu Machine

  • And so much more!

All these things will be done on Google Colab which means it doesn’t matter what processor and computer you have. It is super easy to use and plus point is that you have Free GPU to use in your notebook.

BERT | Sentiment Prediction | Multi Class Prediction Problem

1
Welcome

We will start with the introduction of BERT and we will develop the NLP model. Thereafter, we will deploy the ml model on AWS.

2
Introduction
3
DO NOT SKIP IT | Download Working Files!!!
4
What is BERT
5
What is ktrain
6
Going Deep Inside ktrain Package
7
Notebook Setup
8
Must Read This!!!
9
Installing ktrain
10
Loading Dataset
11
Train-Test Split and Preprocess with BERT
12
BERT Model Training
13
Testing Fine Tuned BERT Model
14
Saving and Loading Fine Tuned Model

Fine Tuning BERT for Disaster Tweets Classification

1
Resources Folder
2
BERT Intro - Disaster Tweets Dataset Understanding
3
Download Dataset
4
Target Class Distribution
5
Number of Characters Distribution in Tweets
6
Number of Words, Average Words Length, and Stop words Distribution in Tweets
7
Most and Least Common Words
8
One-Shot Data Cleaning
9
Disaster Words Visualization with Word Cloud
10
Classification with TFIDF and SVM
11
Classification with Word2Vec and SVM
12
Word Embeddings and Classification with Deep Learning Part 1
13
Word Embeddings and Classification with Deep Learning Part 2
14
BERT Model Building and Training
15
BERT Model Evaluation

DistilBERT | Faster and Cheaper BERT model from Hugging Face

1
What is DistilBERT?
2
Notebook Setup
3
Data Preparation
4
DistilBERT Model Training
5
Save Model at Google Drive
6
Model Evaluation
7
Download Fine Tuned DistilBERT Model
8
Flask App Preparation
9
Run Your First Flask Application
10
Predict Sentiment at Your Local Machine
11
Build Predict API
12
Deploy DistilBERT Model at Your Local Machine

Deploy Your DistilBERT ML Model at AWS EC2 Windows Machine with Flask

1
Create AWS Account
2
Create Free Windows EC2 Instance
3
Connect EC2 Instance from Windows 10
4
Install Python on EC2 Windows 10
5
Must Read This!!!
6
Install TensorFlow 2 and KTRAIN
7
Run Your First Flask Application on AWS EC2
8
Transfer DistilBERT Model to EC2 Flask Server
9
Deploy ML Model on EC2 Server
10
Make Your ML Model Accessible to the World

Deploy Your DistilBERT ML Model at AWS Ubuntu (Linux) Machine with Flask

1
Install Git Bash and Commander Terminal on Local Computer
2
Create AWS Account
3
Launch Ubuntu Machine on EC2
4
Connect AWS Ubuntu (Linux) from Windows Computer
5
Install PIP3 on AWS Ubuntu
6
Update and Upgrade Your Ubuntu Packages
7
Must Read This!!!
8
Install TensorFlow 2, KTRAIN and Upload DistilBert Model
9
Create Extra RAM from SSD by Memory Swapping
10
Deploy DistilBERT ML Model on EC2 Ubuntu Machine

Deploy Robust and Secure Production Server with NGINX, uWSGI, and Flask

1
NGINX Introduction
2
Virtual Environment Setup
3
Setting Up Flask Server
4
NGINX Running Flask Application
5
NGINX Running uWSGI Application
6
Configuring uWSGI Server
7
Start API Services at System Startup
8
Configuring NGINX with uWSGI, and Flask Server
9
Congrats! You Have Deployed ML Model in Production

Multi-Label Classification | Deploy Facebook's FastText NLP Model in Production

1
What is Multi-Label Classification?
2
FastText Research Paper Review
3
Notebook Setup
4
Data Preparation
5
FastText Model Training
6
FastText Model Evaluation and Saving at Google Drive
7
Creating Fresh Ubuntu Machine
8
Setting Python3 and PIP3 Alias
9
Creating 4GB Extra RAM by Memory Swapping
10
Making Your Server Ready
11
Preparing Prediction APIs
12
Testing Prediction API at Local Machine
13
Testing Prediction API at AWS Ubuntu Machine
14
Configuring uWSGI Server
15
Deploy FastText Model in Production with NGINX, uWSGI, and Flask
You can view and review the lecture materials indefinitely, like an on-demand channel.
Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!
4.5
4.5 out of 5
196 Ratings

Detailed Rating

Stars 5
138
Stars 4
39
Stars 3
6
Stars 2
5
Stars 1
7
Get on Udemy
30-Day Money-Back Guarantee

Includes

10 hours on-demand video
5 articles
Full lifetime access
Access on mobile and TV
Certificate of Completion
Deployment of Machine Learning Models in Production | Python
Category:
Data Science
Teacher
Daniel W
Price:
$29.98 $24
Get Course

Community

For Professionals

  • List Item #1
  • List Item #2
  • List Item #3

For Businesses

  • List Item #1
  • List Item #2
  • List Item #3

We support Sales, Marketing, Account Management and CX professionals. Learn new skills. Share your expertise. Connect with experts. Get inspired.

Linkedin Twitter Facebook

Community

Partnership Opportunities

  • Sponsorships
  • Advertise with us
  • List your Business
  • List your Event
  • List your Course

Company Information

  • About Us
  • Newsroom
  • Careers
  • Our Services
  • Contact us
Contribute now
Layer 1
samcx.com
Logo
Register New Account
Compare items
  • Total (0)
Compare
0