Closed nuoloveheng closed 1 year ago
Thanks for your attention. The F.spdevoxelize() requires 4 input elements in our modified torchsparse library, named torchsparse-u. Please refer to https://github.com/MCG-NJU/LinK/blob/aa2ff1d5be3516253530e8b0200796416ca9e734/detection/torchsparse-u/torchsparse/nn/functional/devoxelize.py#L96 .
So, if you did not provide the kernel size to F.spdevoxelize, the F.spdevoxelize will apply a default $r=2$, which is possibly mismatched with your specific kernel size in https://github.com/MCG-NJU/LinK/blob/aa2ff1d5be3516253530e8b0200796416ca9e734/detection/det3d/models/utils/ts_elk.py#L87
I guess this may also account for your question 2 and the performance issue.
If having more questions, please let me know.
Hi,
Thank you for the great work!
I tried to use pcdet to run Link, I modified SpMiddleResNetFHDELKv3 model. It works, but I had some questions during the debug process.
When I finished training, I found that Link was a little better (1 mAP) than CenterPoint(3d spconv). Is this normal? Is it possible that the changes I made above are causing poor performance?