Build on-device model

Build on-device model

Generate code to run the impulse on an embedded device. When this step is complete use downloadBuild to download the artefacts. Updates are streamed over the websocket API.

post

/api/{projectId}/jobs/build-ondevice-model

Authorizations

ApiKeyAuthenticationJWTAuthenticationJWTHttpHeaderAuthentication

Path parameters

projectIdintegerrequired

Project ID

Query parameters

typestringrequired

The name of the built target. You can find this by listing all deployment targets through listDeploymentTargetsForProject (via GET /v1/api/{projectId}/deployment/targets) and see the format type.

impulseIdinteger

Impulse ID. If this is unset then the default impulse is used.

Body

enginestring · enumrequired

Options: tflite, tflite-eon, tflite-eon-ram-optimized, tensorrt, tensaiflow, drp-ai, tidl, akida, syntiant, memryx, neox, ethos-linux, st-aton

modelTypestring · enum

Options: int8, float32, akida, requiresRetrain

Responses

application/json

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --request POST \
  --url 'https://studio.edgeimpulse.com/v1/api/{projectId}/jobs/build-ondevice-model?type=text' \
  --header 'x-api-key: YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{"engine":"tflite","modelType":"int8"}'

200

200

{
  "success": true,
  "error": "text",
  "id": 12873488112
}

OK