Documentation on the inner workings of these models is found on scikit-learns website here.
As a primer, read the Custom learning blocks page in the Edge Impulse docs and see another example here which also shows how to test the block locally.
For more information read Adding parameters to custom blocks.
To get up-to-date data from your project:
-
Install the Edge Impulse CLI v1.16 or higher.
-
Open a command prompt or terminal window.
-
Fetch new data via:
$ edge-impulse-blocks runner --download-data data/
-
Install the Edge Impulse CLI v1.19.3 or higher.
-
Navigate to the directory with the linear model you want to push to edge impulse.
-
Initialize the block:
$ edge-impulse-blocks init # Answer the questions, select "Classification" or "Regression" based on the block you wish to install for 'What type of data does this model operate on?'
-
Push the block:
$ edge-impulse-blocks push
-
The block is now available under any of your projects. Depending on the data your block operates on, you can add it via:
- Classification: Create impulse > Add learning block > Classification, then select the block via 'Add an extra layer' on the 'Classifier' page.
- Regression: Create impulse > Add learning block > Regression, then select the block via 'Add an extra layer' on the 'Regression' page.
Or you can select the block on the "Impulse design" page