Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[WiP] Sen4Map inheritance class change to geobench-compatible datamodule and dataset classes #227

Open
wants to merge 7 commits into
base: main
Choose a base branch
from

Conversation

MinasMayth
Copy link
Collaborator

Issue first raised in #226, Sen4map dataclass and datamodule classes currently only inherit from pytorch lightning, which is functionally adequate for terratorch but will not work with benchmark. I have updated the datamodule class to inherit from NonGeoDataModule, which required a few extra changes.

To get the Sen4map datamodule class to work with inheritance from NonGeoDataModule I had to define a custom augmentation self.aug = AugmentationSequential(K.RandomEqualize3D(), data_keys=None), is this okay? What is the default augmentation and why does it only (seemingly) work for BCHW tensors and not BCDHW tensors?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant