Reference

Evaluation Settings

Look up the controls that affect prediction generation, scoring, and the tutorial Fog comparison.

Prediction Generation controls which outputs and scenario coverage are available. Evaluation selects measurements and criteria from that retained Prediction Set. If new settings require predictions that are not present, generate a new Prediction Set first.

Inputs and inference

The example values below describe the Helmet tutorial. They are not universal defaults for every model or task.

ControlPurposeHelmet tutorial value
DatasetImported samples and reference labelsHelmet v2 full dataset
Model / API ProfileSource that produces predictionsHelmet YOLO26 detector, a local YOLO model
Class labelsNames in model output order; align them with dataset labelsClass 0: helmet
Input width / heightFixed dimensions required by the selected model640 × 640 pixels
Model runnerCompatible inference implementationYOLO
Dataset splitWhich partition supplies samplesValidation
Sample scopeAll selected-split samples or a configured subsetRandom examples: 100 of 195; seed 42
Minimum object confidenceFilters detections below the chosen confidence0.25
Duplicate-box overlapOverlap threshold for suppressing duplicate detections0.5

Increasing minimum confidence can remove false positives and also remove valid low-confidence detections. Changing it changes the prediction evidence. Keep it fixed when you want to compare only the effect of a robustness transform.

The duplicate-box setting controls inference postprocessing; it does not replace the matching rule used by Detection mAP 50-95.

For supported dataset and model files, use the format table.

Robustness coverage and scoring

ControlMeaningExample
TransformModification applied to inputsFog
SeveritySelected image-transform level; integer 1 through 53
SeedNon-negative base seed for stochastic transforms0
Performance metricMeasurement compared between clean and transformed inputsDetection mAP 50-95
Maximum allowed degradation (%)Acceptance limit from 0 to 100; blank means no criterion20

A severity label selects a transform recipe. It does not describe a percentage of fog, and the same severity number means different settings for different transforms. The degradation limit changes the decision rule, not the image transformation.

Fog settings by severity

SeverityFog strengthWibble decay
11.52.0
22.02.0
32.51.7
42.51.5
53.01.4

Fog is stochastic. Preserve the base seed, sample identities, input preparation, and runtime version as well as the severity. The result and report retain the resolved parameters used by that run; use those recorded values when comparing or reproducing results.

What requires a new record?

ChangeNext action
Model weights, dataset contents, inference thresholds, split, or sample scopePrepare compatible inputs and generate a new Prediction Set
Add a transform or severity absent from the sealed setGenerate a set containing the required coverage
Change metrics or criteria with compatible retained evidenceCreate a new Evaluation using the sealed set
Change report wording or included sectionsEdit the report draft and export a new report

See Metrics, Thresholds, and Robustness for score interpretation and Evaluation Presets for reusing a reviewed configuration.