Machine Learning Model Deployment using Docker Container

Model deployment is the next and very important steps once you finalized your model training and development. There are many methods available to deploy the models depending upon the type of serving. There are many serving methods like batch serving, online serving, real time serving or live streaming based serving. In this article I am going to explain one of the deployment mechanism which does online serving using APIs. So I will be explaining how to deploy models using Docker container and run them on production efficiently and reliably.

Topics Covered:

1. Model Training – IRIS multi-classification Model
2. Create an API using Python Flask
3. Create a Docker File
4. Build Docker file to generate a docker Image (You need docker desktop running)
5. Create and run the container using the image build in above step
6. Finally Deploy Model using Docker Container
7. Test the API by sending the test data for prediction
8. Test the API using curl request and test data as csv file
9. Explore running container terminal

I have created a video to explain the step by step approach on model deployment using docker container with all the above topics mentioned. Please watch the video and you can ask your queries using the comment section.

Hope you find the content useful. Let me know your thoughts or any queries using the comments section.

Thank You !