Deploy pretrained model

Deploy pretrained model

post

Takes in a TFLite file and builds the model and SDK. 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.

Authorizations

ApiKeyAuthenticationJWTAuthenticationJWTHttpHeaderAuthentication

Path parameters

projectIdintegerrequired

Project ID

Query parameters

impulseIdintegeroptional

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

Body

modelFileBase64stringrequired

A base64 encoded pretrained model

modelFileTypestring · enumrequiredAvailable options:

deploymentTypestringrequired

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.

enginestring · enumoptionalAvailable options:

modelInfoobjectrequired

representativeFeaturesBase64stringoptional

A base64 encoded .npy file containing the features from your validation set (optional for onnx and saved_model) - used to quantize your model.

deployModelTypestring · enumoptionalAvailable options:

useConverterstring · enumoptional

Optional, use a specific converter (only for ONNX models).

Available options:

Responses

application/json

all ofoptional

post

HTTPcURLJavaScriptPython

POST /v1/api/{projectId}/jobs/deploy-pretrained-model HTTP/1.1
Host: studio.edgeimpulse.com
x-api-key: YOUR_API_KEY
Content-Type: application/json
Accept: */*
Content-Length: 323

{
  "modelFileBase64": "text",
  "modelFileType": "tflite",
  "deploymentType": "text",
  "engine": "tflite",
  "modelInfo": {
    "input": {
      "inputType": "time-series",
      "frequencyHz": 1,
      "windowLengthMs": 1
    },
    "model": {
      "modelType": "classification",
      "labels": [
        "text"
      ]
    }
  },
  "representativeFeaturesBase64": "text",
  "deployModelType": "int8",
  "useConverter": "onnx-tf"
}

200

OK

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