Skip to content

Conversation

@CharlesAuthier
Copy link
Collaborator

Add the option to read a multilayers GPKG when is read by the AOI function.

Plus tests for the entire check_gdf_load function.



def check_gdf_load(gdf):
def check_gdf_load(gdf: Union[str, Path, gpd.GeoDataFrame]) -> gpd.GeoDataFrame:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

good job Charles! I like how you improved this part.

[multi_layers, geopkg],
ignore_index=True
)
return multi_layers
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In general, I understand why it makes sense to know if the label gpkg is a multi-layer or not. But do we have label gpkg in practice? I thought we always have a single-layer single-class gpkg for training? If this is not true, then I need to adjust my tiling script too.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We mustly use single-layer single-class, but we want to also support multi-classes and Pierre told me that the GPKG will be multi layer.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@CharlesAuthier let's discuss it altogether with Mathieu next week because it will require many potential adjustments to the code.

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.

2 participants