search

NVIDIA / MinkowskiEngine

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
https://nvidia.github.io/MinkowskiEngine
Other
2.43k stars 360 forks source link

Update quantization.py #469

Closed TB5z035 closed 1 year ago

TB5z035 commented 2 years ago

torch.Tensor.is_cuda is an attribute, not a function this pr will solve the TypeError when calling sparse_quantize when using torch.Tensor as input image

anandcu3 commented 2 years ago

The same issue reoccurs on line #L286 as well in the same file. Check issue #474 and PR https://github.com/NVIDIA/MinkowskiEngine/pull/475