Get config

Get config

Get config

GEThttps://studio.edgeimpulse.com/v1/api/{projectId}/optimize/config

Path parameters

projectId*integer

Project ID

Response

200

OK

Body

application/json

success*boolean

Whether the operation succeeded

errorstring

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

namestring

targetLatency*integer

Target latency in MS

Example: 0

targetDevice*object

Target device

compilerarray of string

precisionarray of string

trainingCyclesinteger

Maximum number of training cycles

Example: 5

tuningMaxTrialsinteger

Maximum number of trials

Example: 2

tuningWorkersinteger

Maximum number of parallel workers/jobs

Example: 1

initialTrialsinteger

Number of initial trials

Example: 5

optimizationRoundsinteger

Number of optimization rounds

Example: 3

trialsPerOptimizationRoundinteger

Number of trials per optimization round

Example: 3

minMACCSnumber

maxMACCSnumber

tuningAlgorithmenum

Tuning algorithm to use to search hyperparameter space

randomhyperbandbayesiancustom

notificationOnCompletionboolean

importProjectMetricsboolean

Whether to import metrics for previous EON tuner runs in the same project to accelerate the hyperparameter search process

importResourceMetricsboolean

Whether to import resource usage (RAM/ROM/latency) metrics to accelerate the hyperparameter search process

numImportProjectMetricsnumber

Number of project trials to import

numImportResourceMetricsnumber

Number of resource usage trials to import

enableSEMboolean

Enable standard error of the mean (SEM)

accuracySEMnumber

Standard error of the trial accuracy mean

latencySEMnumber

Standard error of the trial latency mean

optimizationObjectivesarray of object

Hyperparameter optimization objectives and corresponding weights

rawObjectivesstring

Hyperparameter optimization objectives + weights in string format

optimizationPrecisionenum

Model variant to optimize for

float32int8

earlyStoppingboolean

Enable trial level early stopping based on loss metrics during training

earlyStoppingWindowSizenumber

Stops the EON tuner if the feasible (mean) objective has not improved over the past “window_size” iterations

earlyStoppingImprovementBarnumber

Threshold (in [0,1]) for considering relative improvement over the best point.

MOMFboolean

Enable Multi-fidelity Multi-Objective optimization

verboseLoggingboolean

Enable verbose logging

disableConstraintsboolean

Disable search constraints

disableDeduplicateboolean

Disable trial deduplication

tunerSpaceOptionsobject

spacearray of TunerSpaceImpulse (object)

List of impulses specifying the EON Tuner search space

searchSpaceTemplateobject

Search space template

deviceobject

Request

JavaScriptCurlPython

const response = await fetch('https://studio.edgeimpulse.com/v1/api/{projectId}/optimize/config', {
    method: 'GET',
    headers: {},
});
const data = await response.json();

Response

200

{
  "success": false,
  "error": "text",
  "name": "text",
  "targetLatency": 0,
  "targetDevice": {
    "name": "cortex-m4f-80mhz",
    "ram": 1024,
    "rom": 1024
  },
  "compiler": [
    "text"
  ],
  "precision": [
    "text"
  ],
  "trainingCycles": 5,
  "tuningMaxTrials": 2,
  "tuningWorkers": 1,
  "initialTrials": 5,
  "optimizationRounds": 3,
  "trialsPerOptimizationRound": 3,
  "minMACCS": 0,
  "maxMACCS": 0,
  "tuningAlgorithm": "random",
  "notificationOnCompletion": false,
  "importProjectMetrics": false,
  "importResourceMetrics": false,
  "numImportProjectMetrics": 0,
  "numImportResourceMetrics": 0,
  "enableSEM": false,
  "accuracySEM": 0,
  "latencySEM": 0,
  "optimizationObjectives": [
    {
      "objective": "text",
      "label": "text",
      "weight": 0
    }
  ],
  "rawObjectives": "text",
  "optimizationPrecision": "float32",
  "earlyStopping": false,
  "earlyStoppingWindowSize": 0,
  "earlyStoppingImprovementBar": 0,
  "MOMF": false,
  "verboseLogging": false,
  "disableConstraints": false,
  "disableDeduplicate": false,
  "space": [
    {
      "inputBlocks": [],
      "dspBlocks": [],
      "learnBlocks": [
        []
      ]
    }
  ],
  "searchSpaceTemplate": {
    "identifier": "speech_keyword",
    "classification": false,
    "anomaly": false,
    "regression": false
  }
}