detectree2

Models moved from repo to Zenodo to resolve bandwidth issues

Multi-temporal prediction combination.
Multi-class outputs.

Some changes to how the file paths are constructed in tile_data to allow more flexibility for non-conventional crs

to_traintest_function tweaked to support cases where there is limited available data. It is now possible to not reserve any data for testing (keeping it all for training/validation). Through the strict argument it is also possible to control whether no overlap in the buffer of training/validation tiles and test tiles is enforced.

This flexibility should help users who have limited data to train on.

Minor updates to the clean_crown function to help handle crs and indexing issues

Some fixes to the tile_data_train function were implemented to stop misalignment on tiles along the edge of a raster scene

Some cleaning of the repo to align with publication in Remote Sensing in Ecology and Conservation

clean_crowns function now:

• can filter crowns based on confidence
• prevents occasionally outputting a pandas data

Updated notes in the tutorial help guide clean/useful outputs

First full release of detectree2

Full Changelog: https://github.com/PatBall1/detectree2/compare/dtree...1.0