Giters

paperswithcode / sotabench-api

Easily benchmark Machine Learning models on selected tasks and datasets

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Make clear which subset - 'val' or 'test' (or other)

RJT1990 opened this issue · comments

commented
  • Need to say in the library if it's validation or test.
  • When doing PwC integration, need to also add new field specifying the dataset subset.

For example, I don't have Cityscapes test data, only validation data. But PWC evaluates on the test set, whereas the library will evaluate on the validation set.