Deploy pretrained model

Deploy pretrained model

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.

post

/api/{projectId}/jobs/deploy-pretrained-model

Authorizations

ApiKeyAuthenticationJWTAuthenticationJWTHttpHeaderAuthentication

Path parameters

projectIdintegerrequired

Project ID

Query parameters

impulseIdinteger

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

Body

modelFileBase64stringrequired

A base64 encoded pretrained model

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 · enum

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

representativeFeaturesBase64string

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

modelFileTypestring · enumrequired

Options: tflite, onnx, saved_model, lgbm, xgboost, pickle

deployModelTypestring · enum

Options: int8, float32

useConverterstring · enum

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

Options: onnx-tf, onnx2tf

modelInfoobjectrequired

Responses

application/json

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --request POST \
  --url 'https://studio.edgeimpulse.com/v1/api/{projectId}/jobs/deploy-pretrained-model' \
  --header 'x-api-key: YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{"modelFileBase64":"text","deploymentType":"text","engine":"tflite","modelFileType":"tflite","deployModelType":"int8","useConverter":"onnx-tf","modelInfo":{"input":{"frequencyHz":1,"windowLengthMs":1,"inputType":"time-series"},"model":{"modelType":"classification","labels":[null]}}}'

200

200

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

OK