Evaluate job result

Get evaluate job result, containing detailed performance statistics for every possible variant of the impulse.

GET /api/{projectId}/deployment/evaluate

Try it

Evaluate job result

cURL

curl --request GET \
  --url https://studio.edgeimpulse.com/v1/api/{projectId}/deployment/evaluate \
  --header 'x-api-key: <api-key>'

200

{
  "success": true,
  "result": [
    {
      "modelType": "int8",
      "learnBlockId": 123,
      "learnBlockType": "anomaly",
      "confusionMatrix": {},
      "trainingLabels": [
        "<string>"
      ],
      "classificationLabels": [
        "<string>"
      ],
      "accuracy": {
        "raw": 123,
        "withAnomaly": 123
      },
      "totalWindowCount": 123,
      "totalCorrectWindowCount": {
        "raw": 123,
        "withAnomaly": 123
      }
    }
  ],
  "error": "<string>"
}

Authorizations

x-api-key · string · header · required

Path Parameters

projectId · integer · required

Project ID

Query Parameters

impulseId · integer

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

Response

200 - application/json

OK

success · boolean · required

Whether the operation succeeded

result · object[] · required

Show child attributes

result. modelType · enum<string> · required

The type of model

Available options: int8, float32, akida, requiresRetrain

result. learnBlockId · integer · required

The learning block this model variant is from

result. learnBlockType · enum<string> · required

The type of learning block (anomaly, keras, keras-transfer-image, keras-transfer-kws, keras-object-detection, keras-regression). Each behaves differently.

Available options: anomaly, anomaly-gmm, keras, keras-transfer-image, keras-transfer-kws, keras-object-detection, keras-regression, keras-akida, keras-akida-transfer-image, keras-akida-object-detection, keras-visual-anomaly

result. confusionMatrix · object · required

A map from actual labels to predicted labels, where actual labels are listed in trainingLabels and possible predicted labels are listed in classificationLabels.

Show child attributes

result.confusionMatrix. {key} · object

Show child attributes

result.confusionMatrix.{key}. {key} · object

Show child attributes

result.confusionMatrix.{key}.{key}. raw · number

The value based on the model alone

result.confusionMatrix.{key}.{key}. withAnomaly · number

The value including the result of anomaly detection

result. trainingLabels · string[] · required

The labels present in the model's training data. These are all present in the first dimension of the confusion matrix.

result. classificationLabels · string[] · required

The possible labels resulting from classification. These may be present in the second dimension of the confusion matrix.

result. accuracy · object · required

The model's accuracy as a percentage

Show child attributes

result.accuracy. raw · number

The value based on the model alone

result.accuracy. withAnomaly · number

The value including the result of anomaly detection

result. totalWindowCount · integer

The total number of windows that were evaluated

result. totalCorrectWindowCount · object

The total number of windows that the model classified correctly

Show child attributes

result.totalCorrectWindowCount. raw · number

The value based on the model alone

result.totalCorrectWindowCount. withAnomaly · number

The value including the result of anomaly detection

error · string

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