Classify sample by learn block

This API is deprecated, use classifySampleByLearnBlockV2 (/v1/api/{projectId}/classify/anomaly-gmm/v2/{blockId}/{sampleId}) instead. Classify a complete file against the specified learn block. This will move the sliding window (dependent on the sliding window length and the sliding window increase parameters in the impulse) over the complete file, and classify for every window that is extracted.

GET /api/{projectId}/classify/anomaly-gmm/{blockId}/{sampleId}

Try it

Classify sample by learn block

cURL

curl --request GET \
  --url https://studio.edgeimpulse.com/v1/api/{projectId}/classify/anomaly-gmm/{blockId}/{sampleId} \
  --header 'x-api-key: <api-key>'

200

{
  "success": true,
  "classifications": [
    {
      "learnBlock": {
        "id": 2,
        "type": "anomaly",
        "name": "NN Classifier",
        "dsp": [
          27
        ],
        "title": "Classification (Keras)",
        "createdBy": "createImpulse",
        "createdAt": "2023-11-07T05:31:56Z"
      },
      "result": [
        {
          "idle": 0.0002,
          "wave": 0.9998,
          "anomaly": -0.42
        }
      ],
      "minimumConfidenceRating": 123,
      "expectedLabels": [
        {
          "startIndex": 123,
          "endIndex": 123,
          "label": "<string>"
        }
      ],
      "thresholds": [
        {
          "key": "min_score",
          "description": "Score threshold",
          "helpText": "Threshold score for bounding boxes. If the score for a bounding box is below this the box will be discarded.",
          "value": 0.5,
          "suggestedValue": 123,
          "suggestedValueText": "<string>"
        }
      ],
      "anomalyResult": [
        {
          "boxes": [
            {
              "label": "<string>",
              "x": 123,
              "y": 123,
              "width": 123,
              "height": 123,
              "score": 123
            }
          ],
          "scores": [
            [
              123
            ]
          ],
          "meanScore": 123,
          "maxScore": 123
        }
      ],
      "structuredResult": [
        {
          "boxes": [
            [
              123
            ]
          ],
          "scores": [
            123
          ],
          "mAP": 123,
          "f1": 123,
          "precision": 123,
          "recall": 123,
          "labels": [
            "<string>"
          ],
          "debugInfoJson": "{\n    \"y_trues\": [\n        {\"x\": 0.854, \"y\": 0.453125, \"label\": 1},\n        {\"x\": 0.197, \"y\": 0.53125, \"label\": 2}\n    ],\n    \"y_preds\": [\n        {\"x\": 0.916, \"y\": 0.875, \"label\": 1},\n        {\"x\": 0.25, \"y\": 0.541, \"label\": 2}\n    ],\n    \"assignments\": [\n        {\"yp\": 1, \"yt\": 1, \"label\": 2, \"distance\": 0.053}\n    ],\n    \"normalised_min_distance\": 0.2,\n    \"all_pairwise_distances\": [\n        [0, 0, 0.426],\n        [1, 1, 0.053]\n    ],\n    \"unassigned_y_true_idxs\": [0],\n    \"unassigned_y_pred_idxs\": [0]\n}\n"
        }
      ],
      "details": [
        {
          "boxes": [
            [
              123
            ]
          ],
          "labels": [
            123
          ],
          "scores": [
            123
          ],
          "mAP": 123,
          "f1": 123
        }
      ],
      "objectDetectionLastLayer": "mobilenet-ssd"
    }
  ],
  "sample": {
    "sample": {
      "id": 2,
      "filename": "idle01.d8Ae",
      "signatureValidate": true,
      "created": "2023-11-07T05:31:56Z",
      "lastModified": "2023-11-07T05:31:56Z",
      "category": "training",
      "coldstorageFilename": "<string>",
      "label": "healthy-machine",
      "intervalMs": 16,
      "frequency": 62.5,
      "originalIntervalMs": 16,
      "originalFrequency": 62.5,
      "deviceType": "<string>",
      "sensors": [
        {
          "name": "accX",
          "units": "<string>"
        }
      ],
      "valuesCount": 123,
      "added": "2023-11-07T05:31:56Z",
      "boundingBoxes": [
        {
          "label": "<string>",
          "x": 123,
          "y": 123,
          "width": 123,
          "height": 123
        }
      ],
      "boundingBoxesType": "object_detection",
      "chartType": "chart",
      "isDisabled": true,
      "isProcessing": true,
      "processingError": true,
      "isCropped": true,
      "projectId": 123,
      "sha256Hash": "<string>",
      "signatureMethod": "HS256",
      "signatureKey": "<string>",
      "deviceName": "<string>",
      "totalLengthMs": 123,
      "thumbnailVideo": "<string>",
      "thumbnailVideoFull": "<string>",
      "processingJobId": 123,
      "processingErrorString": "<string>",
      "metadata": {},
      "projectOwnerName": "<string>",
      "projectName": "<string>",
      "projectLabelingMethod": "single_label",
      "structuredLabels": [
        {
          "startIndex": 123,
          "endIndex": 123,
          "label": "<string>"
        }
      ],
      "structuredLabelsList": [
        "<string>"
      ],
      "createdBySyntheticDataJobId": 123,
      "imageDimensions": {
        "width": 123,
        "height": 123
      },
      "videoUrl": "<string>",
      "videoUrlFull": "<string>"
    },
    "payload": {
      "device_type": "DISCO-L475VG-IOT01A",
      "sensors": [
        {
          "name": "accX",
          "units": "<string>"
        }
      ],
      "values": [
        [
          123
        ]
      ],
      "device_name": "ac:87:a3:0a:2d:1b",
      "cropStart": 0,
      "cropEnd": 128
    },
    "totalPayloadLength": 123
  },
  "windowSizeMs": 2996,
  "windowIncreaseMs": 10,
  "alreadyInDatabase": true,
  "error": "<string>",
  "warning": "<string>"
}

Authorizations

x-api-key · string · header · required

Path Parameters

projectId · integer · required

Project ID

sampleId · integer · required

Sample ID

blockId · integer · required

Block ID

Response

200 - application/json

OK

success · boolean · required

Whether the operation succeeded

classifications · object[] · required

Show child attributes

classifications. learnBlock · object · required

Show child attributes

classifications.learnBlock. id · integer · required

Identifier for this block. Make sure to up this number when creating a new block via getNewBlockId, and don't re-use identifiers. If the block hasn't changed, keep the ID as-is. ID must be unique across the project and greather than zero (>0).

Required range: x >= 1

classifications.learnBlock. type · 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

classifications.learnBlock. name · string · required

Block name, will be used in menus. If a block has a baseBlockId, this field is ignored and the base block's name is used instead.

Example:

"NN Classifier"

classifications.learnBlock. dsp · integer[] · required

DSP dependencies, identified by DSP block ID

classifications.learnBlock. title · string · required

Block title, used in the impulse UI

Example:

"Classification (Keras)"

classifications.learnBlock. createdBy · string

The system component that created the block version (createImpulse | clone | tuner). Cannot be set via API.

Example:

"createImpulse"

classifications.learnBlock. createdAt · string<date-time>

The datetime that the block version was created. Cannot be set via API.

classifications. result · object[] · required

Classification result, one item per window.

Show child attributes

classifications.result. {key} · number

Example:

[
  {
    "idle": 0.0002,
    "wave": 0.9998,
    "anomaly": -0.42
  }
]

classifications. minimumConfidenceRating · number · required

DEPRECATED, see "thresholds" instead. The minimum confidence rating for this block. For regression, this is the absolute error (which can be larger than 1).

classifications. expectedLabels · object[] · required

An array with an expected label per window.

Show child attributes

classifications.expectedLabels. startIndex · integer · required

Start index of the label (e.g. 0)

classifications.expectedLabels. endIndex · integer · required

End index of the label (e.g. 3). This value is inclusive, so { startIndex: 0, endIndex: 3 } covers 0, 1, 2, 3.

classifications.expectedLabels. label · string · required

The label for this section.

classifications. thresholds · object[] · required

List of configurable thresholds for this block.

Show child attributes

classifications.thresholds. key · string · required

Identifier to reference the threshold. You'll need to refer to the threshold by this key when you set the threshold).

Example:

"min_score"

classifications.thresholds. description · string · required

User-friendly description of the threshold.

Example:

"Score threshold"

classifications.thresholds. helpText · string · required

Additional help text (shown in the UI under a "?" icon)

Example:

"Threshold score for bounding boxes. If the score for a bounding box is below this the box will be discarded."

classifications.thresholds. value · number · required

Current value of the threshold

Example:

0.5

classifications.thresholds. suggestedValue · number

If the threshold has a suggested value, e.g. a max. absolute error for regression projects; or the min. anomaly score for visual anomaly detection, then this is the numeric value of that threshold.

classifications.thresholds. suggestedValueText · string

If the threshold has a suggested value, e.g. a max. absolute error for regression projects; or the min. anomaly score for visual anomaly detection, then this is the stringified value of that threshold.

classifications. anomalyResult · object[]

Anomaly scores and computed metrics for visual anomaly detection, one item per window.

Show child attributes

classifications.anomalyResult. boxes · object[]

For visual anomaly detection. An array of bounding box objects, (x, y, width, height, score, label), one per detection in the image. Filtered by the minimum confidence rating of the learn block.

Show child attributes

classifications.anomalyResult.boxes. label · string · required

classifications.anomalyResult.boxes. x · number · required

classifications.anomalyResult.boxes. y · number · required

classifications.anomalyResult.boxes. width · number · required

classifications.anomalyResult.boxes. height · number · required

classifications.anomalyResult.boxes. score · number · required

classifications.anomalyResult. scores · number[][]

2D array of shape (n, n) with raw anomaly scores for visual anomaly detection, where n can be calculated as ((1/8 of image input size)/2 - 1). The scores corresponds to each grid cell in the image's spatial matrix.

classifications.anomalyResult. meanScore · number

Mean value of the scores.

classifications.anomalyResult. maxScore · number

Maximum value of the scores.

classifications. structuredResult · object[]

Results of inferencing that returns structured data, such as object detection

Show child attributes

classifications.structuredResult. boxes · number[][] · required

For object detection. An array of bounding box arrays, (x, y, width, height), one per detection in the image.

classifications.structuredResult. scores · number[] · required

For object detection. An array of probability scores, one per detection in the image.

classifications.structuredResult. mAP · number · required

For object detection. A score that indicates accuracy compared to the ground truth, if available.

classifications.structuredResult. f1 · number · required

For FOMO. A score that combines the precision and recall of a classifier into a single metric, if available.

classifications.structuredResult. precision · number · required

A measure of how many of the positive predictions made are correct (true positives).

classifications.structuredResult. recall · number · required

A measure of how many of the positive cases the classifier correctly predicted, over all the positive cases.

classifications.structuredResult. labels · string[]

For object detection. An array of labels, one per detection in the image.

classifications.structuredResult. debugInfoJson · string

Debug info in JSON format

Example:

"{\n \"y_trues\": [\n {\"x\": 0.854, \"y\": 0.453125, \"label\": 1},\n {\"x\": 0.197, \"y\": 0.53125, \"label\": 2}\n ],\n \"y_preds\": [\n {\"x\": 0.916, \"y\": 0.875, \"label\": 1},\n {\"x\": 0.25, \"y\": 0.541, \"label\": 2}\n ],\n \"assignments\": [\n {\"yp\": 1, \"yt\": 1, \"label\": 2, \"distance\": 0.053}\n ],\n \"normalised_min_distance\": 0.2,\n \"all_pairwise_distances\": [\n [0, 0, 0.426],\n [1, 1, 0.053]\n ],\n \"unassigned_y_true_idxs\": [0],\n \"unassigned_y_pred_idxs\": [0]\n}\n"

classifications. details · object[]

Structured outputs and computed metrics for some model types (e.g. object detection), one item per window.

Show child attributes

classifications.details. boxes · number[][]

Bounding boxes predicted by localization model

classifications.details. labels · number[]

Labels predicted by localization model

classifications.details. scores · number[]

Scores predicted by localization model

classifications.details. mAP · number

For object detection, the COCO mAP computed for the predictions on this image

classifications.details. f1 · number

For FOMO, the F1 score computed for the predictions on this image

classifications. objectDetectionLastLayer · enum<string>

Available options: mobilenet-ssd, fomo, yolov2-akida, yolov5, yolov5v5-drpai, yolox, yolov7, yolo-pro, tao-retinanet, tao-ssd, tao-yolov3, tao-yolov4, yolov11, yolov11-abs

sample · object · required

Show child attributes

sample. sample · object · required

Show child attributes

sample.sample. id · integer · required

Example:

2

sample.sample. filename · string · required

Example:

"idle01.d8Ae"

sample.sample. signatureValidate · boolean · required

Whether signature validation passed

Example:

true

sample.sample. created · string<date-time> · required

Timestamp when the sample was created on device, or if no accurate time was known on device, the time that the file was processed by the ingestion service.

sample.sample. lastModified · string<date-time> · required

Timestamp when the sample was last modified.

sample.sample. category · enum<string> · required

Available options: training, testing, post-processing

Example:

"training"

sample.sample. coldstorageFilename · string · required

sample.sample. label · string · required

Example:

"healthy-machine"

sample.sample. intervalMs · number · required

Interval between two windows (1000 / frequency). If the data was resampled, then this lists the resampled interval.

Example:

16

sample.sample. frequency · number · required

Frequency of the sample. If the data was resampled, then this lists the resampled frequency.

Example:

62.5

sample.sample. originalIntervalMs · number · required

Interval between two windows (1000 / frequency) in the source data (before resampling).

Example:

16

sample.sample. originalFrequency · number · required

Frequency of the sample in the source data (before resampling).

Example:

62.5

sample.sample. deviceType · string · required

sample.sample. sensors · object[] · required

Show child attributes

sample.sample.sensors. name · string · required

Name of the axis

Example:

"accX"

sample.sample.sensors. units · string · required

Type of data on this axis. Needs to comply to SenML units (see https://www.iana.org/assignments/senml/senml.xhtml).

sample.sample. valuesCount · integer · required

Number of readings in this file

sample.sample. added · string<date-time> · required

Timestamp when the sample was added to the current acquisition bucket.

sample.sample. boundingBoxes · object[] · required

Show child attributes

sample.sample.boundingBoxes. label · string · required

sample.sample.boundingBoxes. x · integer · required

sample.sample.boundingBoxes. y · integer · required

sample.sample.boundingBoxes. width · integer · required

sample.sample.boundingBoxes. height · integer · required

sample.sample. boundingBoxesType · enum<string> · required

Available options: object_detection, constrained_object_detection

sample.sample. chartType · enum<string> · required

Available options: chart, image, video, table

sample.sample. isDisabled · boolean · required

True if the current sample is excluded from use

sample.sample. isProcessing · boolean · required

True if the current sample is still processing (e.g. for video)

sample.sample. processingError · boolean · required

Set when processing this sample failed

sample.sample. isCropped · boolean · required

Whether the sample is cropped from another sample (and has crop start / end info)

sample.sample. projectId · integer · required

Unique identifier of the project this sample belongs to

sample.sample. sha256Hash · string · required

Data sample SHA 256 hash (including CBOR envelope if applicable)

sample.sample. signatureMethod · string

Example:

"HS256"

sample.sample. signatureKey · string

Either the shared key or the public key that was used to validate the sample

sample.sample. deviceName · string

sample.sample. totalLengthMs · number

Total length (in ms.) of this file

sample.sample. thumbnailVideo · string

sample.sample. thumbnailVideoFull · string

sample.sample. processingJobId · integer

Set when sample is processing and a job has picked up the request

sample.sample. processingErrorString · string

Error (only set when processing this sample failed)

sample.sample. metadata · object

Sample free form associated metadata

Show child attributes

sample.sample.metadata. {key} · string

sample.sample. projectOwnerName · string

Name of the owner of the project this sample belongs to

sample.sample. projectName · string

Name of the project this sample belongs to

sample.sample. projectLabelingMethod · enum<string>

What labeling flow the project this sample belongs to uses

Available options: single_label, object_detection

sample.sample. structuredLabels · object[]

Show child attributes

sample.sample.structuredLabels. startIndex · integer · required

Start index of the label (e.g. 0)

sample.sample.structuredLabels. endIndex · integer · required

End index of the label (e.g. 3). This value is inclusive, so { startIndex: 0, endIndex: 3 } covers 0, 1, 2, 3.

sample.sample.structuredLabels. label · string · required

The label for this section.

sample.sample. structuredLabelsList · string[]

sample.sample. createdBySyntheticDataJobId · integer

If this sample was created by a synthetic data job, it's referenced here.

sample.sample. imageDimensions · object

Show child attributes

sample.sample.imageDimensions. width · integer · required

sample.sample.imageDimensions. height · integer · required

sample.sample. videoUrl · string

Video link, cropped and in original resolution.

sample.sample. videoUrlFull · string

Video link in original resolution.

sample. payload · object · required

Sensor readings and metadata

Show child attributes

sample.payload. device_type · string · required

Device type, for example the exact model of the device. Should be the same for all similar devices.

Example:

"DISCO-L475VG-IOT01A"

sample.payload. sensors · object[] · required

Array with sensor axes

Show child attributes

sample.payload.sensors. name · string · required

Name of the axis

Example:

"accX"

sample.payload.sensors. units · string · required

Type of data on this axis. Needs to comply to SenML units (see https://www.iana.org/assignments/senml/senml.xhtml).

sample.payload. values · number[][] · required

Array of sensor values. One array item per interval, and as many items in this array as there are sensor axes. This type is returned if there are multiple axes.

sample.payload. device_name · string

Unique identifier for this device. Only set this when the device has a globally unique identifier (e.g. MAC address).

Example:

"ac:87:a3:0a:2d:1b"

sample.payload. cropStart · integer

New start index of the cropped sample

Example:

0

sample.payload. cropEnd · integer

New end index of the cropped sample

Example:

128

sample. totalPayloadLength · integer · required

Total number of payload values

windowSizeMs · integer · required

Size of the sliding window (as set by the impulse) in milliseconds.

Example:

2996

windowIncreaseMs · integer · required

Number of milliseconds that the sliding window increased with (as set by the impulse)

Example:

10

alreadyInDatabase · boolean · required

Whether this sample is already in the training database

error · string

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

warning · string