Miao Ziliang

Results 5 comments of Miao Ziliang

same problem, you have to make sure the tensor type of features is torch.float32.

I also encounter the same error using RTX 4090 RuntimeError: at /tmp/pip-req-build-up7naarj/src/gpu.cu:100

@chrischoy Same problem still unsolved, could you please provide any suggestions? RTX4090, python=3.8, pytorch=1.10.0-cu111, pytorch-lightning=1.9.0, MinkowskiEngine=0.5.4 If `quantization_mode=ME.SparseTensorQuantizationMode.UNWEIGHTED_AVERAGE`, it will cause RuntimeError: ``` File "/home/user/Projects/MosPretrain/scripts/train.py", line 101, in main() File...

Same question. I want to use all lidar scans of Motion dataset, instead of "the first 1 second of each of the 9-second windows". https://github.com/waymo-research/waymo-open-dataset/issues/740