cadwallader113
cadwallader113
Thank you for experimenting. It's interesting that older GPUs are faster in testing. The original implementation nutonomy / second.pytorch is also implemented in pytorch, but is it the GPU hardware...
Thank you very much. I will continue to investigate your project to some extent.
I attempted to check the execution time of the PillarEncoder function. According to the result, `nn.BatchNorm1d` seems to take 500 ~ 600ms. offset_pt_center_t: 0.000000 ms offset_pi_center_t: 12.212276 ms encoder_t: 0.000000...
cuda is 10.1 GTX 1080. I use test.py, epoch_160.pth, training/velodyne_reduced/000134.bin. There was an error in my measurement. I'm sorry. The processing time for nn.BatchNorm1d was roughly 1ms. It seems that...
thanks for this good solution! I’ll give it a try and share your results.
thank you for the sample program. I changed pytorch and cuda to be the same as yours, but the difference was small... But like you, iterating solved the conv1d bottleneck...
Thank you for your reply. Great result. In my tests, test.py speed was around 15fps on GTX1080. So, if I want to increase from 15fps to 42fps, I have to...