search

KuanchihHuang / MonoDTR

MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer (CVPR 2022)
MIT License
132 stars 19 forks source link

Error in view #18

Open Kiet0712 opened 6 months ago

Kiet0712 commented 6 months ago

Hi! Thank for you great work! image I saw that in monodtr_core you have do this. I think it must be img_feat = img_feat.permute(0,2,3,1).view(N,H*W,C)