I would like to understand how I can put into practice in some system, the model that I create with Deep learning or machine learning. I see several tutorials teaching to create a very simple structure of deep learning, and in the end bringing results of approximately 90% acurracy. I understand that it worked.
But what now? How to use this? How to put this template on my system?
There are a few ways, I'd say the following two are the most commonly used.
1) API:
There are several examples of APIs that do model harnessing (see: link ). An endpoint is created that receives a new observation and returns the value predicted by the algorithm.
2) Batch Scoring
The model is anchored daily, for example, for all new observations.
Given these two ways there are some frameworks that help you do this without having to worry about scalability, etc. These are:
In practice, it is easier to make an API in any language to do this than to use some framework.
