You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Many datasets like Sentinel2 have a different resolution per band. Currently we don't handle this and things crash when you try to concatenate bands with different shape. There are a few options for how to handle this:
Automatically resample to the highest resolution
Allow user to specify resolution to resample to
Store bands with different resolution in different dict keys
Option 3 makes it hard to automatically detect the "image" keys during data augmentation, but offers the greatest flexibility for modeling. Option 1 and 2 aren't mutually exclusive, and are probably the easiest to implement in the short term.
We also need to add transforms for resampling.
The text was updated successfully, but these errors were encountered:
Many datasets like Sentinel2 have a different resolution per band. Currently we don't handle this and things crash when you try to concatenate bands with different shape. There are a few options for how to handle this:
Option 3 makes it hard to automatically detect the "image" keys during data augmentation, but offers the greatest flexibility for modeling. Option 1 and 2 aren't mutually exclusive, and are probably the easiest to implement in the short term.
We also need to add transforms for resampling.
The text was updated successfully, but these errors were encountered: