aniqueakhtar

Failing to understand a portion of xdconv

6

Hello, Recently I was going through your xdconv section of the code and I think there's a bug but I fail to understand how it is still working. Let me...

Code # 1: ``` coordinates = torch.IntTensor([[0, 0], [0, 0], [0, 1], [0, 2]]) coordinates = coordinates.to(device) manager = ME.CoordinateManager(D=1) key, (unique_map, inverse_map) = manager.insert_and_map(coordinates, [1]) print(key) print(unique_map) print(inverse_map) torch.all(coordinates[unique_map]...

Unable to install on Ubuntu 20.04 for RTX 3090 with GCC 9.3.0

7

previously, I was able to install Minkowski on 'RTX 1080 Ti' with 'gcc 7.5' using the following command: ``` conda create -n mink python=3.7 conda activate mink conda install pytorch=1.8.1...

Issues with up_ratio

5

I am trying to trian the model for up_ratio=8 but I realized there are a lot of error in the code that doesn't make it possible to train for that...