Description
Course Deploy Machine Learning Models on GCP + AWS Lambda (Docker). Hello everyone, welcome to one of the most practical courses on machine learning and deep learning model generation. What is model deployment: Let’s say you have a model after doing some rigorous training on your dataset. But now what to do with this model. You have tested your model with a test data set which is good. You got very good accuracy with this model. But the real test comes when live data hits your model. So this course is about how to serialize your model and deploy it on the server. After participating in this course:
- You will be able to deploy a model on a cloud server.
- You will be one step ahead in your machine learning journey.
- You can add another machine learning skill to your resume.
What is going to be covered in this course?
1. Introduction to the course
In this section, I will teach you the basic idea of deploying a model about the design workflow of a machine learning system and the various cloud deployment options available.
2. Flask Crash course
In this section you will learn about the Flask crash course for those of you who are not familiar with the Flask framework as we are going to implement the model with the help of this Flask web development framework available in Python.
3. Deployment model with flask
In this section you will learn how to Serialize and Deserialize a scikit-learn model and deploy a proprietary Flask-based web service. To test the Web API, we will use the Postman API test tool and the Python requests module.
4. Serialize Deep Learning Model Tensorflow
In this section you will learn how to serialize and serialize keras model in Fashion MNIST Dataset.
5. Deploy to the Heroku cloud
In this section, we will deploy the flower classification dataset model that we created in the last section to the Heroku-Pass cloud solution.
6. Deploy in the Google Cloud
In this section, you will learn how to deploy the model in different Google cloud services such as Google Cloud Performance, Google Application Engine, and Google Managed Artificial Intelligence Cloud.
7. Deploy to Amazon AWS Lambda
In this section, you will learn how to deploy the flower classification model on an AWS lambda function.
8. Deployment on Amazon AWS ECS with Docker Container
In this section, we’ll see how to put an application inside a Docker container and deploy it to Amazon ECS (Elastic Container Service).
What you will learn in the Deploy Machine Learning Models on GCP + AWS Lambda (Docker) course
-
Model deployment process
-
Various options are available for deploying the model
-
Scikit-learn, run Tensorflow 2.0 model with Flask Web Framework
-
Model deployment in Google cloud performance, application engine
-
Presenting the model through Google’s artificial intelligence platform
-
Run the Prediction API on Heroku Cloud
-
Serialize and Deserialize the model via Scikit-learn and Tensorflow
-
Deploying the model to Amazon AWS Lambda
-
Install the flower prediction model with Docker
-
Docker Container deployment in Amazon Container Services (ECS)
This course is suitable for people who
- Anyone who knows ML and wants to move towards model deployment
- Anyone who wants to know how to put a machine learning program into production
Course specifications Deploy Machine Learning Models on GCP + AWS Lambda (Docker)
- Publisher: Udemy
- teacher: Ankit Mistry
- Training level: beginner to advanced
- Training duration: 4 hours and 17 minutes
Headlines of the Deploy Machine Learning Models on GCP + AWS Lambda (Docker) course on October 2021
Prerequisites of the course Deploy Machine Learning Models on GCP + AWS Lambda (Docker)
- Basics of Python Programming
- Basic knowledge of Web development
Course images
Sample video of the course
Installation guide
After Extract, view with your favorite Player.
Subtitle: None
Quality: 720p
download link
File(s) password: www.downloadly.ir
File size 1
1.7 GB
Be the first to comment