search

PRBonn / lidar-bonnetal

Semantic and Instance Segmentation of LiDAR point clouds for autonomous driving
http://semantic-kitti.org
MIT License
915 stars 204 forks source link

[BUG REPORT] IoU eval conf_matrix_ accumulation doesn't work #74

Closed chengdazhi closed 3 years ago

chengdazhi commented 3 years ago

Heads up! On my machine, the line self.conf_matrix = self.conf_matrix.index_put_(tuple(idxs), self.ones, accumulate=True) does nothing for entries in conf_matrix that is above 16777216. You can try:

a = torch.Tensor([[0, 0],[0,16777216]]) print(a) a.indexput((torch.ones(100).long(), torch.ones(100).long()), torch.ones(100),accumulate=True) print(a)

to see if you can reproduce. Hope you didn't use the same code for your test server.

tano297 commented 3 years ago

Did you modify your conf_matrix to be float? This is a known issue for float32, that is why the confusion matrix is long

chengdazhi commented 3 years ago

Ah right, I was using Pytorch 1.4 and followed this comment: https://github.com/PRBonn/lidar-bonnetal/issues/22#issuecomment-603078234 I should have paid attention to your reply to that comment.