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
We recently added a new NLCD dataset. Instead of duplicating the class mapping and cmap in ChesapeakeCVPR, we should use them from the NLCD dataset.
Rationale
Code duplication is bad.
Implementation
from .nlcdimportNLCDcmap=NLCD.cmap
Alternatives
Only reason to not duplicate them is in case we add Alaska to NLCD, which contains classes that don't exist in ChesapeakeCVPR. This doesn't affect cmap, but may affect the class mapping if we want to minimize the number of predicted classes.
Additional information
No response
The text was updated successfully, but these errors were encountered:
Summary
We recently added a new NLCD dataset. Instead of duplicating the class mapping and cmap in ChesapeakeCVPR, we should use them from the NLCD dataset.
Rationale
Code duplication is bad.
Implementation
Alternatives
Only reason to not duplicate them is in case we add Alaska to NLCD, which contains classes that don't exist in ChesapeakeCVPR. This doesn't affect cmap, but may affect the class mapping if we want to minimize the number of predicted classes.
Additional information
No response
The text was updated successfully, but these errors were encountered: