xinge008/Cylinder3D

Generalization Experiment-Related Questions

Opened this issue · 0 comments

We modified the point cloud data format of the Nuscenes dataset to the point cloud data format of SemanticKitti. Then we used the pre-trained weights provided by the author for SemanticKitti to make predictions. However, the results we obtained were inferior. We are unsure if the issue lies with our operations or the network itself. Has anyone done similar generalization experiments?