Build on-device model
Generate code to run the impulse on an embedded device. When this step is complete use downloadHistoricDeployment to download the artefacts. Updates are streamed over the websocket API.
POST
Build on-device model
Query Parameters
Body
application/json
Model type (e.g. i8 quantized or unoptimized) for all learn blocks. If some learn blocks do not have the required model type, they'll fall back to their default type (e.g. float32). If not specified (nor modelType specified), falls back to learn block's "selectedModelType".
Available options:
int8, float32, akida Response
200 - application/json
OK