curl --request GET \
--url https://studio.edgeimpulse.com/v1/api/{projectId}/performance-calibration/parameter-sets \
--header 'x-api-key: <api-key>'{
"success": true,
"parameterSets": [
{
"detections": [
{
"time": 123,
"label": "<string>"
}
],
"isBest": true,
"labels": [
"<string>"
],
"aggregateStats": {
"falsePositiveRate": 123,
"falseNegativeRate": 123
},
"stats": [
{
"label": "<string>",
"truePositives": 123,
"falsePositives": 123,
"falseNegatives": 123,
"trueNegatives": 123,
"falsePositiveRate": 123,
"falseNegativeRate": 123,
"falseNegativeTimes": [
123
],
"falsePositiveDetails": [
{
"type": "incorrect",
"detectionTime": 123,
"groundTruthLabel": "<string>",
"groundTruthStart": 123,
"sampleIds": [
123
]
}
]
}
],
"params": {
"type": "standard",
"version": 1,
"parametersStandard": {
"averageWindowDurationMs": 1000,
"detectionThreshold": 0.8,
"suppressionMs": 500
}
},
"windowSizeMs": 123
}
],
"error": "<string>"
}Get performance calibration parameter sets
curl --request GET \
--url https://studio.edgeimpulse.com/v1/api/{projectId}/performance-calibration/parameter-sets \
--header 'x-api-key: <api-key>'{
"success": true,
"parameterSets": [
{
"detections": [
{
"time": 123,
"label": "<string>"
}
],
"isBest": true,
"labels": [
"<string>"
],
"aggregateStats": {
"falsePositiveRate": 123,
"falseNegativeRate": 123
},
"stats": [
{
"label": "<string>",
"truePositives": 123,
"falsePositives": 123,
"falseNegatives": 123,
"trueNegatives": 123,
"falsePositiveRate": 123,
"falseNegativeRate": 123,
"falseNegativeTimes": [
123
],
"falsePositiveDetails": [
{
"type": "incorrect",
"detectionTime": 123,
"groundTruthLabel": "<string>",
"groundTruthStart": 123,
"sampleIds": [
123
]
}
]
}
],
"params": {
"type": "standard",
"version": 1,
"parametersStandard": {
"averageWindowDurationMs": 1000,
"detectionThreshold": 0.8,
"suppressionMs": 500
}
},
"windowSizeMs": 123
}
],
"error": "<string>"
}Project ID
Impulse ID. If this is unset then the default impulse is used.
File
Whether the operation succeeded
Show child attributes
Whether this is considered the best parameter set
All of the possible labels in the detections array
Show child attributes
The times in ms at which false negatives occurred. These correspond to specific items in the ground truth.
The details of every false positive detection.
Show child attributes
The type of false positive. Incorrect is when a detection matches the wrong ground truth. Duplicate is when the same ground truth was detected more than once. The first correct detection is considered a true positive but subsequent detections are considered false positives. Spurious is when the detection was not associated with any ground truth.
incorrect, duplicate, spurious The time of the detection in milliseconds
The label of any associated ground truth
The start time of any associated ground truth
All of the sample IDs in the affected region
Show child attributes
The post-processing algorithm type.
standard The version number of the post-processing algorithm.
1
Show child attributes
The length of the averaging window in milliseconds.
1000
The minimum threshold for detection, from 0-1.
0.8
The amount of time new matches will be ignored after a positive result.
500
The size of the input block window in milliseconds.
Optional error description (set if 'success' was false)
Was this page helpful?