search

hailanyi / VirConv

Virtual Sparse Convolution for Multimodal 3D Object Detection
https://arxiv.org/abs/2303.02314
Apache License 2.0
276 stars 39 forks source link

Questions about the leaderboard's inference time #58

Closed jisoo0-0 closed 9 months ago

jisoo0-0 commented 9 months ago

Hi, thank you for your wonderful work.

I wonder if this version of the code is the one you reported on the official site of the KITTI competition in terms of the environment(1 core @ 2.5 Ghz (C/C++)).

Thanx.

hailanyi commented 9 months ago

No, it is based on 3090 GPU and pytorch framework.

jisoo0-0 commented 9 months ago

Thank you

Chrislai502 commented 7 months ago

Hey, a quick follow up question on this, does inference only need 1 single GPU? Thanks in advance!