Test pretrained model using image data

Test pretrained model using image data

post

Test out a pretrained model (using image data) - upload first via uploadPretrainedModel. If you want to deploy a pretrained model from the API, see startDeployPretrainedModelJob. This will transform raw image data (e.g. RGB to grayscale, resize) before classifying. To classify raw features, see testPretrainedModel.

Authorizations

ApiKeyAuthenticationJWTAuthenticationJWTHttpHeaderAuthenticationOAuth2

Path parameters

projectIdintegerRequired

Project ID

Query parameters

impulseIdintegerOptional

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

Body

imageFileBase64stringRequired

A base64 encoded input image file

modelone ofRequired

or

or

Responses

200

OK

application/json

Responseall of

post

HTTPcURLJavaScriptPython

POST /v1/api/{projectId}/pretrained-model/test-image HTTP/1.1
Host: studio.edgeimpulse.com
x-api-key: YOUR_API_KEY
Content-Type: application/json
Accept: */*
Content-Length: 137

{
  "imageFileBase64": "text",
  "input": {
    "resizeMode": "squash",
    "inputScaling": "0..1"
  },
  "model": {
    "modelType": "classification",
    "labels": [
      "text"
    ]
  }
}

200

OK

{
  "success": true,
  "error": "text",
  "result": {
    "ANY_ADDITIONAL_PROPERTY": 1
  },
  "boundingBoxes": [
    {
      "label": "text",
      "x": 1,
      "y": 1,
      "width": 1,
      "height": 1,
      "score": 1
    }
  ]
}