search

MCG-NJU / SparseBEV

[ICCV 2023] SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos
https://arxiv.org/abs/2308.09244
MIT License
339 stars 24 forks source link

Deployment questions #33

Open BarathwajAnandan opened 11 months ago

BarathwajAnandan commented 11 months ago

Hi, Awesome work! I was exploring to do inference using TensorRT and was wondering if the layers are supported or if you guys had any plugins if you have tested it already!

Thanks.

afterthat97 commented 11 months ago

Hi, we haven't tried TensorRT yet, as we are not experts on this field. SparseBEV can be implemented by native pytorch (the CUDA operator is optional and only 15% faster), so there should be no problem using TensorRT.

We welcome your contributions, feel free to post a pull request if you have any progress!