Open robmarkcole opened 2 weeks ago
Why not always compute both macro and micro statistics in all trainers? I would welcome a PR that adds this.
In addition to class wise or instead of? I think that would be nice to have the complete set - with the classwise as optional otherwise the list of metrics can get very long
Ah sorry, yeah I meant macro + micro + classwise. As long as that doesn't noticeably slow down training time it should be fine.
Summary
This FR is to add support for classwise metrics to the segmentation trainer
Rationale
There can be many classes in a dataset and we want class specific metrics
Implementation
Using the approach of @isaaccorley as here with ClasswiseWrapper and enabled by an optional arg to the segmentation trainer,
classwise_metrics: bool = False
. To support this an additionallabels: Optional[List[str]] = None
arg will also be addedAlternatives
None
Additional information
No response