search

remydubois / lsnms

Large Scale Non maximum Suppression. This project implements a O(nlog(n)) approach for non max suppression, useful for object detection ran on very large images such as satellite or histology, when the number of instances to prune becomes very large.
63 stars 5 forks source link

resolve_issue_19 #20

Closed chottAA5208 closed 1 year ago

chottAA5208 commented 1 year ago

Resolve: https://github.com/remydubois/lsnms/issues/19

remydubois commented 1 year ago

Thanks for the PR !

It just needs a little re-work for numba compiling to pass, see my comments. Also, the test in test/test_nms.py needs to be modified accordingly to the new indexing, otherwise, I think it will fail in its current state. I will try to have pass on it today.