v1.2.2
v1.2.2 contains several minor changes:
- Added a check to make sure that a group data loader is used whenever
n_groups_per_batch
ordistinct_groups
are passed in as arguments toexamples/run_expt.py
. (#79) - Data augmentations now only transform
x
by default. Setdo_transform_y
when initializing theWILDSSubset
to modify bothx
andy
. (#77) - For FasterRCNN, we now use the PyTorch implementation of
smooth_l1_loss
instead of the custom torchvision implementation, which was removed in torchvision v0.10. - Updated the requirements to include torchvision, scipy, and scikit-learn. Previously, torchvision was only needed for the example scripts. However, it is now also used for computing metrics in the GlobalWheat-WILDS dataset, so we have moved it into the core set of requirements.