Closed mihsamusev closed 3 years ago
I'm not sure what's wrong here, never seen this one before. Do you mind dropping an email to anjul.ten@gmail.com? We can maybe figure this out over a quick call sometime. Thanks!
If you trained it prior to my pull request, remove the background class from the config file and change all corresponding class indices back to the previous version. You don't need the background class except for debugging purposes. I think, this might be the cause for this.
Closing this one for now.
Hi, thanks for terrific work here and on Medium. I have pulled the code dated from this commit https://github.com/tyagi-iiitv/PointPillars/commit/0e2784c24503a03c705ff773cd673229a4227d27 and then trained a model for 2 days on KITTI dataset without any issues. As an output i obtained
./logs/model.h
. Then i saw that thepoint_pillars_prediction.py
was inclomplete and pulled latest commit https://github.com/tyagi-iiitv/PointPillars/commit/0e2784c24503a03c705ff773cd673229a4227d27Running a code prediction code gave me this:
My environment is a
scrin/dev-spconv
Docker container with CUDA 10.1 and latest tensorflow / pytorch preinstalled:nvcc --version
givesCuda compilation tools, release 10.1, V10.1.243
pip list | grep tensor
gives