Closed MasterSkepticista closed 10 months ago
This is for some rare classification datasets where some examples do not have a single label. An example is our ImageNet-ReaL dataset, which has ~3000 validation images with no label. According to the official metric, these should be ignored, rather than always scored as wrong, which is what'd happen if the mask wasn't updated.
A padding mask with
_mask=0
is built here for evaluation datasets, which also implicitly setslabel
to be a vector of all zeros for the fake example. https://github.com/google-research/big_vision/blob/184d1201eb34abe7da84fc69f84fd89a06ad43c4/big_vision/input_pipeline.py#L149Why is there a need to update the mask here?
https://github.com/google-research/big_vision/blob/184d1201eb34abe7da84fc69f84fd89a06ad43c4/big_vision/evaluators/classification.py#L39