Number of filters in Fire modules not consistent with the SqueezeSeg paper about lidar-bonnetal HOT 3 CLOSED

Hello,
Good catch. After reading the paper I decided that the easiest way to do exactly the same network was to use their code, for a fair comparison. When I did, I did not see that discrepancy. But if you look here https://github.com/BichenWuUCB/SqueezeSeg/blob/master/src/nets/squeezeSeg.py , it looks like the author in the code is using squeeze*4 everywhere. Only some layers keep the dimensions.

I do not recommend using squeezeseg for the semantic kitti dataset. Go for one of the darknet backbones, they achieve significantly higher IoU.

Closing this, as it is not an issue. But feel free to keep commenting

from lidar-bonnetal.

Yeah, I also try the Darknet, how about the Focal loss they claim in the SqueezeSegV2 paper? Do you use it in this code?

from lidar-bonnetal.

I tried it, but it did not make a lot of difference vs inverse frequency scaling. That is very dataset dependent...

from lidar-bonnetal.