Model Training and Deployment

For every attribute, once data has been organized to a certain level of confidence and completion, you can click the to train a new machine learning model - based on the starter models + user feedback provided within xBlox. This training will take a few hours to complete, at the end of which you have ML model to organize your data for a specific attribute.

This process can be repeated for each attribute in the taxonomy. Selecting Actions → Deploy, will string together these ML models in the form a graph that’s ready to be deployed in the server (location) of your choice. An API key is generated to invoke the graph.

Once deployed, the graph will be ready to serve predictions when invoked using the API (with a payload containing datapoints' images). The API spec is available here.