Skip to content

Latest commit

 

History

History
19 lines (15 loc) · 1.04 KB

AddingModels.md

File metadata and controls

19 lines (15 loc) · 1.04 KB

Guide to add models

To add a model, the following guide will help you

  • The model needs to be added to TinyVerse
  • Say for example, to add a model for audio tasks
  • Head over to <root>/tinyml-tinyverse/tinyml_tinyverse/common/models
  • In the directory, add a <model_name>.py file or add the model to any of the existing generic_*_models.py
  • and add the corresponding model name to __init__.py in the model_dict

At this stage, the TinyVerse package can function independently with the model

However, to make sure the Modelmaker also can run the model, we need to add a few more files

  • Head over to <root>/tinyml-modelmaker/tinyml_modelmaker/ai_modules/common/timeseries/training/tinyml_tinyverse/
  • Note: In the above path timeseries needs to be replaced with the respective ai_module, i.e audio or vision etc
  • In case the added model is for a classification task, then go to the script: Eg.: timeseries_classification.py
  • Add the model details under model_urls, _model_descriptions and enabled_models_list