You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The content in semantic-kitti.yaml is the distribution ratio of classes in the SemanticKITTI dataset. You have to calculate the total number of points of each class in your custom dataset to get this ratio. But, you don't need this information to train PolarSeg unless you want to try some other losses, like weighted cross-entropy.
I need to train for custom dataset with less classes.
I referred to #2.
But i had a doubt on How to get the values of content:
PolarSeg/semantic-kitti.yaml
Line 72 in 172c650
Kindly help
The text was updated successfully, but these errors were encountered: