Robin Cole
Robin Cole
@adamjstewart can confirm, but I assume we want to keep the current behaviour
This can be swapped for `X,y = shap.datasets.california()`
@adamjstewart not sure about this Also not sure why seeing this - have run `ruff format`
Updated ruff, no issues locally ``` Successfully installed ruff-0.14.6 ⚡ Update-seg-and-class-metrics ~/torchgeo ruff format torchgeo/trainers/segmentation.py 1 file left unchanged ⚡ Update-seg-and-class-metrics ~/torchgeo ruff check torchgeo/trainers/segmentation.py All checks passed! ``` confusing...
In use an error is raised since ClasswiseWrapper returns dicts: ``` ValueError: The `.compute()` return of the metric logged as 'val_Accuracy' must be a tensor. Found {'multiclassaccuracy_background': tensor(0.9996, device='cuda:0'), 'multiclassaccuracy_solar':...
@SkafteNicki thanks for clarifying, and yes ignoring these values in averages is the goal 👍
@FederCO23 care to add a datamodule too? Also this dataset is only 4 channel, don't suppose you investigated adding the other channels too?
Test failures same as https://github.com/microsoft/torchgeo/pull/2707#issuecomment-2908777476
@FederCO23 hit the `Update branch` button as the failing test is fixed on main
Plus 1