Learn

Upload a pretrained model

Upload a pretrained model and receive info back about the input/output tensors. If you want to deploy a pretrained model from the API, see startDeployPretrainedModelJob.

post/api/{projectId}/pretrained-model/upload

Request

Base URL
https://studio.edgeimpulse.com/v1
Auth
- API key in header x-api-key
- or API key in cookie jwt
- or API key in header x-jwt-token
- or OAuth 2
  Authorization code/v1/oauth/authorize
  Client credentials
  Implicit/v1/oauth/authorize
  Password
  Token URL/v1/oauth/token
TypeScript
https://skmtc.dev/edgeimpulse/apis/edge-impulse-api/docs/api/:projectId/pretrained-model/upload/post.ts
A function with typed inputs. Its response is checked against the schema.

Path parameters

projectIdinteger required

Project ID

Query parameters

impulseIdinteger

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

Request body multipart/form-data

modelFilestring binary required

modelFileNamestring required

modelFileType'tflite' | 'onnx' | 'saved_model' required

representativeFeaturesstring binary

devicestring

MCU used for calculating latency, query latencyDevices in listProject for a list of supported devices (and use the "mcu" property here). If this is kept empty then we'll show an overview of multiple devices.

overrideInputShapeinteger[]

Optional for ONNX files: overrides the input shape of the model. This is highly suggested if the model has dynamic dimensions. If this field is not set, then all dynamic dimensions will be set to '1'.

additionalFilesstring[]

Response

successboolean required

Whether the operation succeeded

errorstring

Optional error description (set if 'success' was false)

idinteger required

Job identifier. Status updates will include this identifier.

Example response

{
  "id": 12873488112
}

Changes

No recorded changes to this operation across all 1 revision of this API.