When you enroll through our links, we may earn a small commission—at no extra cost to you. This helps keep our platform free and inspires us to add more value.
Deploy Machine Learning Models on GCP + AWS Lambda (Docker)
How to Serialize - Deserialize model with scikit-learn & Deployment on Heroku, AWS Lambda, ECS, Docker and Google Cloud
This Course Includes
udemy
4.3 (449 reviews )
4h 18m 
english
Online - Self Paced
professional certificate
Udemy
About Deploy Machine Learning Models on GCP + AWS Lambda (Docker)
Disclaimer :
This course requires you to download
Anaconda
and
Docker Desktop
from their official websites. If you are a Udemy Business user, please check with your employer before downloading any software to ensure compliance with your organization’s policies. Hello everyone, welcome to one of the most practical course on
Machine learning and Deep learning model deployment
production level.
_What is model deployment :_
Let's say you have a model after doing some rigorous training on your data set. But now what to do with this model. You have tested your model with testing data set that's fine. You got very good accuracy also with this model. But real test will come when live data will hit your model. So This course is about
How to serialize your model and deployed on server
.
_After attending this course :_
you will be able to
deploy a model on a cloud server
.
You will be
ahead one step in a machine learning
journey.
You will be able to
add one more machine learning skill
in your resume. What is going to cover in this course?
_1. Course Introduction_
In this section I will teach you about what is model deployment basic idea about machine learning system design workflow and different deployment options are available at a cloud level.
_2. Flask Crash course_
In this section you will learn about crash course on flask for those of you who is not familiar with flask framework as we are going to deploy model with the help of this flask web development framework available in Python.
_3. Model Deployment with Flask_
In this section you will learn how to
Serialize
and Deserialize
scikit-learn
model and will deploy owner
flask
based Web services. For testing
Web API
we will use
Postman
API testing tool and Python
requests
module.
_4. Serialize Deep Learning Tensorflow Model_
In this section you will learn how to serialize and deserialize keras model on
Fashion MNIST
Dataset.
_5. Deploy on Heroku cloud_
In this section you will learn how to deploy already serialized
flower classification data set
model which we have created in a last section will deploy on Heroku cloud -
Pass
solution.
_6. Deploy on Google cloud_
In this section you will learn how to deploy model on different Google cloud services like Google
Cloud function,
app engine
and Google managed
AI cloud
.
_7. Deploy on Amazon AWS Lambda_
In this section, you will learn how to deploy flower classification model on AWS lambda function.
_8. Deploy on Amazon AWS ECS with Docker Container_
In This section, we will see how to put application inside docker container and deploy it inside Amazon ECS (Elastic Container Services) This course comes with 30 days money back guarantee. No question ask.
So what are you waiting for just enroll it today.
I will see you inside class.
Happy learning Ankit Mistry
What You Will Learn?
- Model Deployment Process .
- Different option available for Model Deployment .
- Deploy Scikit-learn, Tensorflow 2.0 Model with Flask Web Framework .
- Deploy Model on Google cloud function, App engine .
- Serve model through Google AI Platform .
- Run Prediction API on Heroku Cloud .
- Serialize and Deserialize model through Scikit-learn and Tensorflow .
- Deploying model on Amazon AWS Lambda .
- Install Flower prediction model with Docker .
- Deploy Docker Container on Amazon Container Services (ECS).