Newbie here and I only have experience in training machine learning models on Jupyter notebook along with test/validate the model accuracy.

I would like to move on and learn how I can deploy machine learning model for real world usage, for example, a web page that take input such as "age", "height", "diet" and return the chance of obesity (just a random example).

I now have the webpage available (just the frontend) and I would like to ask how can I deploy my machine learning model to handle high volume of user? (maybe 5000 request??)

The question I have is how do real world company deploy their machine learning model? Should I train a model using Python on Jupyter notebook and attach the model on my Java web server using Deeplearning4j library (inspired by this link

https://towardsdatascience.com/deploying-keras-deep-learning-models-with-java-62d80464f34a )

or should I subscribe to a VM service (Azure/AWS) and deploy a python web application (with/without docker, new to docker as well). My web page will then using post request to get prediction result from python web application.

Any help or advice is greatly appreciated, thanks in advance!!



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.