Deploy a Production Machine Learning model with AWS & React

Focused View

Patrik Szepesi

5:44:31

57 View

01 - Intro

001 Course overview.mp4

03:13

002 What were going to build.mp4

03:16

003 Introduction.mp4

01:37

02 - Setting up SageMaker

001 Setting Up IAM Policies.mp4

09:31

002 Setting Up SageMaker.mp4

05:16

003 Launching our SageMaker notebook.mp4

05:07

external-links.txt

03 - Quick Tips before getting our Data

001 Cost optimazation and other Tips.mp4

05:25

04 - Exploratory data analysis

001 Get data from Kaggle Part 1.mp4

05:03

002 Get Data from Kaggle Part 2.mp4

00:41

003 Important.mp4

00:26

004 Visualizing images.mp4

11:54

005 Correction.mp4

01:02

006 Resizing images(Theory).mp4

03:53

007 Computer Vision Part 1.mp4

02:22

008 Computer Vision Part 2.mp4

10:08

009 Resizing our images(Coding).mp4

11:11

010 Check the resized images.mp4

04:04

011 Data Visualization.mp4

03:17

012 Creating our DataFrame for Visualization.mp4

10:07

013 Creating our Bar Graphs.mp4

02:17

014 Making our Graphs nicer.mp4

04:23

05 - Setting up our AWS training Job

001 What are .lst Files.mp4

03:50

002 Creating Pandas DataFrame for .lst files.mp4

07:28

003 Creating our .lst files.mp4

03:45

004 Upload images and .lst files to S3.mp4

06:04

005 Correction and Verify Upload.mp4

01:16

006 Setting up our Estimator object for training.mp4

08:41

007 IMPORTANT, Correction for Max Runs.html

008 Setting up Hyperparameter Tuning.mp4

08:01

009 Setting up Hyperparameters ranges.mp4

06:53

010 Correction.mp4

02:15

011 Setting up our Training Job.mp4

10:34

012 Starting our Training Job.mp4

02:17

06 - Evaluating and Testing our Trained model

001 Evaluating our Training Job.mp4

07:48

002 Deploying our model locally.mp4

05:17

003 Getting our First Inference.mp4

05:46

004 Constructing our confusion matrix.mp4

10:42

005 Recall, Precision, F1 Score.mp4

05:41

006 Shutting down our Endpoint.mp4

01:05

07 - Deploying our model Endpoint to Amazon API Gateway

001 Creating IAM Policy for our lambda function.mp4

06:00

002 Coding our Lambda function.mp4

11:55

003 Creating Our API Gateway.mp4

05:29

004 Adding Endpoint name to Lambda.mp4

01:01

005 Image shape for Inference.mp4

00:59

006 Testing Our Endpoint with Postman.mp4

04:26

007 Setting up Lambda Concurrency.mp4

04:17

08 - Creating our web application

001 Source Code.html

002 Setting up our MongoDB database.mp4

04:45

003 Downloading source code from Github.mp4

03:32

004 Launching our web application locally.mp4

09:35

005 Set Axios URL to our Endpoint.mp4

01:03

006 MERN app walkthrough Part 1.mp4

20:34

007 Start your Endpoint.mp4

01:10

008 MERN app walkthrough Part 2.mp4

12:27

external-links.txt

09 - Scalability and Security

001 AutoScaling for our Endpoint Part 1.mp4

04:20

002 AutoScaling for our Endpoint Part 2.mp4

05:12

003 Securing our Endpoint Part 1.mp4

03:53

004 Securing our Endpoint Part 2.mp4

01:21

external-links.txt

10 - Deploying our web application to DigitalOcean

001 Creating our DigitalOcean account.mp4

01:24

002 Setting Up our DigitalOcean server.mp4

02:09

003 SSH-ing into our DigitalOcean droplet.mp4

04:28

004 Installing Node.js and NPM to our droplet.mp4

03:15

005 Creating our Frontend and Backend repositories.mp4

03:02

006 Clone Repos from Github and Install Nginx.mp4

06:23

007 Create env Files and Setting up MongoDB.mp4

04:25

008 Starting our Backend.mp4

03:10

009 Running our Frontend.mp4

01:37

010 Changing IP addresses.mp4

03:18

011 Testing on random images from the Internet.mp4

02:48

external-links.txt

11 - Outro

001 Delete Amazon SageMaker Endpoint.mp4

01:18

002 Clean Up and Next Steps.mp4

03:39

003 Final Step Delete Elastic File System.html

004 Thank you.html

Description

Build a Scalable and Secure, Deep Learning Image Classifier with SageMaker, Next.js, Node.js, MongoDB & DigitalOcean

What You'll Learn?

Deploy a production ready robust, scalable, secure Machine Learning application
Set up Hyperparameter Tuning in AWS
Find the best Hyperparameters with Bayesian search
Use Matplotlib, Numpy, Pandas, Seaborn in SageMaker
Use AutoScaling for our deployed Endpoints in AWS
Use multi-instance GPU instance for training in AWS
Learn how to use SageMaker Notebooks for any Machine Learning task in AWS
Set up AWS API Gateway to deploy our model to the internet
Secure AWS Endpoints with limited IP address access
Use any custom dataset for training
Set up IAM policies in AWS
Set up Lambda concurrency in AWS
Data Visualization in SageMaker
Learn how to do MLOps in AWS
Build and deploy a MongoDB, Express, Nodejs, React/nextjs application to DigitalOcean
Create an end to end machine learning pipeline all the way from gathering data to deployment
File Mode vs Pipe Mode when training deep learning models on AWS
Use AWS' built in Image Classifier
Create deep learning models with AWS SageMaker
Learn how to access any AWS built in algorithm from AWS ECR
Use CloudWatch logs to monitor training jobs and inferences
Analyze machine learning models with Confusion matrix, F1 score, Recall, and Precision
Access AWS endpoint through a deployed MERN web application running on DigitalOcean
Build a beautiful web application
Learn how to combine AI and Machine Learning with Healthcare
Set up Data Augmentation in AWS
Machine Learning with Python
JavaScript to deploy MERN apps

Who is this for?

Those with some ML experience who are hoping to take their skills to the next step by being able to deploy their deep learning models to production

What You Need to Know?

Any laptop and an internet connection

Some Python and Machine Learning Knowledge

about 15-40 dollars for using AWS resources(Optional, only applies if you follow along with me)

More details

Description
In this course we are going to use AWS Sagemaker, AWS API Gateway, Lambda, React.js, Node.js, Express.js MongoDB and DigitalOcean to create a secure, scalable, and robust production ready enterprise level image classifier. We will be using best practices and setting up IAM policies to first create a secure environment in AWS. Then we will be using AWS' built in SageMaker Studio Notebooks where I am going to show you guys how you can use any custom dataset you want. We will perfrom Exploratory data analysis on our dataset with Matplotlib, Seaborn, Pandas andÂ Numpy. After getting insightful information about dataset we will set up our Hyperparameter Tuning Job in AWS where I will show you guys how to use GPU instances to speed up training and I will even show you guys how to use multi GPU instance training. We will then evaluate our training jobs, and look at some metrics such as Precision, Recall and F1 Score. Upon evaluation we will deploy our deep learning model on AWS with the help of AWS API Gateway and Lambda functions. We will then test our API with Postman, and see if we get inference results. After that is completed we will secure our endpoints and set up autoscaling to prevent latency issues. Finally we will build our web application which will have access to the AWS API. After that we will deploy our web application to DigitalOcean.

Who this course is for:
Those with some ML experience who are hoping to take their skills to the next step by being able to deploy their deep learning models to production

User Reviews

Rating

average 0

Total votes0

Focused display

I am an AWS certified machine learning engineer , working as a machine learning engineer at Blue River Technology, a Silicon Valley company creating computer vision machine learning solutions(such as autonomous vehicles ) for John Deere. I have worked as a data scientist at companies like Morgan Stanley, and I am also participating in several artificial intelligence related researches with Óbuda University. I am here to share the most cutting edge technologies surrounding machine learning and AWS.

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.