PatBall1 / detectree2

Python package for automatic tree crown delineation based on the Detectron2 implementation of Mask R-CNN
https://patball1.github.io/detectree2/
MIT License
148 stars 35 forks source link

Updates in train.py rpn layer and predict.py proprocessing #84

Open WangLuran opened 1 year ago

WangLuran commented 1 year ago

Changing the nms algorithm in rpn layer by considering inter over area instead of inter over union. It inceases the speed of divergence and mask quality and a little in ap50. The overlapping of crowns of different types is also solved. Change in proprocessing in predict.py. Instead of just deleting all crowns with a objectness value less than a threshold, a changed nms algorithm is applied - we use inter over area of masks instead of bounding boxes for a better output.

PatBall1 commented 1 year ago

Thanks for this contribution @WangLuran ! There seems to be a few conflicts that are preventing me from merging. Would you also please comment which functions have been edited (and how)?

WangLuran commented 1 year ago

OK, got it! I will merge the commits and write the comments

ma595 commented 7 months ago

This PR has become stale. @PatBall1 is it still relevant?