Overview

Ekkono Primer is the main software library that encompasses Edge and Crystal. It’s main features are:

  • Model factory – for creating new models
  • Model training – for training models in an offline setting (Edge and Crystal support incremental training)
  • Model tester – for evaluating model performance
  • Model conversion – for converting models to Crystal format (models are per default Edge format)

It also has all of Ekkono’s classes for datasets and other data types that are useful during model development.

Hello World Example

Creating, training and evaluating a model using the Python API.


 1  import ekkono.primer as primer
 2
 3  templ = primer.PipelineTemplate(
 4      primer.AttributeMeta('signal1'),
 5      primer.AttributeMeta('signal2'),
 6      primer.AttributeMeta('signal3'),
 7  )
 8
 9  target = 'signal3'
10
11  model = primer.ModelFactory.create_mlp_model(templ, target)
12  primer.ModelTrainer.train(model, dataset)
13
14  result = primer.ModelTester.get_prediction_tuples(model, dataset)
15  mae = primer.ModelTester.calculate_mae(result)
16  r2 = primer.ModelTester.calculate_r2(result)

Requirements

Python >=3.7 (to use Python bindings).

Intended Use

This library is primarily for use on desktop when models are being developed. I is delivered as a compiled application. Everything required for model inference or incremental training is included in Edge or Crystal.