search

DerrickXuNu / OpenCOOD

[ICRA 2022] An opensource framework for cooperative detection. Official implementation for OPV2V.
https://mobility-lab.seas.ucla.edu/opv2v/
Other
644 stars 99 forks source link

Question about compression using pointpillar. #117

Open Sun1boy opened 9 months ago

Sun1boy commented 9 months ago

When I using opencood/hypes_yaml/point_pillar_intermediate_fusion.yaml for training. I set compression to 4. image Then a RuntimeError occurred: The size of tensor a (70400) must match the size of tensor b (78848) at non-singleton dimension 1 image How did I solve it? Thank you for your help.