Hugues THOMAS
Hugues THOMAS
Go at the place where the bug happens: "blocks.py", line 312, try printing the shapes and of the tensors there, Try printing the max values if the indices, etc. It...
Hi @YdeZ030, Unfortunately, no. Sorry.
Hi @cppcute-pm, The cpp functions is extremely hard to debug. The python debug mode wont work with them. You need to place cout in the cpp file to follow the...
You definitely can. The calibration function is here to simplify the parameter tuning by choosing an appropriate value depending on the point density. But you can set it yourself absolutely.
It does not "need" it. It is just a value you can decide for yourself. In my experiments, I noticed this was a good value as it already reduced the...
Hi @liuzhy71, If you downsample during the forward path, then you also have to compute convolution neighbors during the forward path. If downsampling is super fast, the neighbor computation is...
In the case of inference, the processing time is also reduced. We can achieve a higher processing frequency for offline inference tasks. For online inference in real time, our pipeline...
Check you files, there might be an error in them and you will need to download the dataset again
Hi Tobias, Indeed considering your data, it is not surprising that you have randomly varying VRAM usage and eventually OOM error. With a batch size of 1, you do not...
There is no test set defined on this dataset validation scores are possible