Profile TFLite model

Profile TFLite model

Takes in a TFLite model and returns the latency, RAM and ROM used for this model. Updates are streamed over the websocket API (or can be retrieved through the /stdout endpoint). Use getProfileTfliteJobResult to get the results when the job is completed.

post

/api/{projectId}/jobs/profile-tflite

Authorizations

ApiKeyAuthenticationJWTAuthenticationJWTHttpHeaderAuthentication

Path parameters

projectIdintegerrequired

Project ID

Body

tfliteFileBase64stringrequired

A base64 encoded TFLite file

devicestringrequired

MCU used for calculating latency, query latencyDevices in listProject for a list of supported devices (and use the "mcu" property here).

Responses

application/json

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --request POST \
  --url 'https://studio.edgeimpulse.com/v1/api/{projectId}/jobs/profile-tflite' \
  --header 'x-api-key: YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{"tfliteFileBase64":"text","device":"text"}'

200

200

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

OK