Train model (Keras)

Train model (Keras)

Take the output from a DSP block and train a neural network using Keras. Updates are streamed over the websocket API.

POSThttps://studio.edgeimpulse.com/v1/api/{projectId}/jobs/train/keras/{learnId}

Path parameters

projectId*integer

Project ID

learnId*integer

Learn Block ID, use the impulse functions to retrieve the ID

Body

application/json

modeenum

Whether to use visual or expert mode.

expertvisual

minimumConfidenceRatingnumber

Minimum confidence score, if the neural network scores a sample below this threshold it will be flagged as uncertain.

selectedModelTypeKerasModelTypeEnum (enum)

int8float32akidarequiresRetrain

scriptstring

Raw Keras script (only used in expert mode)

visualLayersarray of KerasVisualLayer (object)

The visual layers for the neural network (only in visual mode).

trainingCyclesinteger

Number of training cycles (only in visual mode).

learningRatenumber

Learning rate (between 0 and 1) (only in visual mode).

batchSizenumber

Batch size used during training (only in visual mode).

trainTestSplitnumber

Train/test split (between 0 and 1)

autoClassWeightsboolean

Whether to automatically balance class weights, use this for skewed datasets.

useLearnedOptimizerboolean

Use learned optimizer and ignore learning rate.

augmentationPolicyImageAugmentationPolicyImageEnum (enum)

The data augmentation policy to use with image input

noneall

augmentationPolicySpectrogramAugmentationPolicySpectrogram (object)

profileInt8boolean

Whether to profile the i8 model (might take a very long time)

skipEmbeddingsAndMemoryboolean

If set, skips creating embeddings and measuring memory (used in tests)

akidaEdgeLearningConfigAkidaEdgeLearningConfig (object)

customValidationMetadataKeystring

If the 'custom validation split' experiment is enabled, this metadata key is used to prevent group data leakage between train and validation datasets.

showAdvancedTrainingSettingsboolean

Whether the 'Advanced training settings' UI element should be expanded.

showAugmentationTrainingSettingsboolean

Whether the 'Augmentation training settings' UI element should be expanded.

customParametersobject

Training parameters, this list depends on the list of parameters that the model exposes.

anomalyCapacityAnomalyCapacity (enum)

Capacity level for visual anomaly detection. Determines which set of default configurations to use. The higher capacity, the higher number of (Gaussian) components, and the more adapted the model becomes to the original distribution

lowmediumhigh

lastShownModelVariantKerasModelVariantEnum (enum)

int8float32akida

lastShownModelEngineModelEngineShortEnum (enum)

tflite-eontflite-eon-ram-optimizedtflite

blockParametersBlockParameters (one of)

Training parameters specific to the type of the learn block. Parameters may be adjusted depending on the model defined in the visual layers. Used for our built-in blocks.

BlockParamsVisualAnomalyPatchcore (object)BlockParamsVisualAnomalyGmm (object)

Response

200

OK

Body

application/json

success*boolean

Whether the operation succeeded

errorstring

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

id*integer

Job identifier. Status updates will include this identifier.

Example: 12873488112

Request

JavaScriptCurlPython

const response = await fetch('https://studio.edgeimpulse.com/v1/api/{projectId}/jobs/train/keras/{learnId}', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({}),
});
const data = await response.json();

Response

200

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