Evaluation configuration¶
Evaluation configuration lives under the Evaluator root object.
Evaluator:
metrics:
SEG:
targets_criterions:
SEG_PRED:
criterions_loader:
Dice:
labels: [1, 2, 3]
Dataset:
...
train_name: SEG_BASELINE
Top-level fields¶
Field |
Type |
Default in code |
Required |
Effect |
|---|---|---|---|---|
|
mapping |
default target criterions loader |
Yes in practice |
Declares what metrics should be computed and between which groups. |
|
mapping |
|
Yes |
Defines how targets and predictions are loaded. |
|
string |
|
Yes in practice |
Names the evaluation output folder. |
metrics¶
The evaluation structure mirrors outputs_criterions, but without the model.
metrics:
sCT:
targets_criterions:
CT;MASK:
criterions_loader:
MAE:
reduction: mean
PSNR:
dynamic_range: None
Structure:
output group → the predicted group to evaluate
targets_criterions→ one or more target groups, optionally composed with;criterions_loader→ one or more metric implementations
Some metrics also accept attributes or write auxiliary datasets. This behavior is
implemented in konfai.evaluator.Evaluator.update() and konfai.metric.measure.
Evaluator.Dataset¶
Evaluation datasets are instantiated through DataMetric.
Common fields:
Field |
Type |
Effect |
|---|---|---|
|
list[str] |
Pairs or merges the datasets needed for evaluation. |
|
mapping |
Defines how the compared tensors are loaded. |
|
object |
Restricts evaluated cases. |
|
string / list / null |
Optional validation selector for a separate JSON report. Supports a case-list file, a list of case names, or a list of case-list files. |
Output files¶
Evaluation writes JSON files, not CSV files. The main outputs are:
Metric_TRAIN.jsonoptionally
Metric_VALIDATION.json
The JSON structure contains:
per-case values under
caseaggregated statistics under
aggregates
This behavior comes from konfai.evaluator.Statistics.write().
Examples¶
See:
examples/Segmentation/Evaluation.ymlexamples/Synthesis/Evaluation.yml