suyunzzz
> Hi @suyunzzz, I don't fully understand your need (what the goal is for your operator). Could you please elaborate a bit more? Hello, zhijian, In the MinkowskiEngine, there are...
> I haven't checked the details of your implementation, but I think you are on the right track. > > From my understanding, you might need to pass `x.s` to...
i use MinkowskiEngine v0.5.4 to train scananet，there are some logs, i dont know where is the reason. ``` 25%|██▍ | 75/301 [01:06 Epoch[4](1280/301): Loss 0.7165 LR: 9.904e-02 Score nan Data...
@abhigoku10 hello, have you trained on semantickitti dataset? what changes should i do if i want to train semantickitti?
anyone has solved this problem?
helllo, same error, ``` xiaokeai1-Z10PE-D8-WS 01/04 14:54:15 ===> Epoch[1](1/102): Loss 2.5535 LR: 1.000e-01 Score 9.130 Data time: 4.7232, Total iter time: 6.3637 xiaokeai1-Z10PE-D8-WS 01/04 14:54:33 ===> Epoch[1](40/102): Loss 1.6340 LR:...
i use docker, and same error was encounterd.
> @suyunzzz this issue hasn't been solved yet, what I did is a wrapper which checks `active.large_pool.current` and if the number of the pool grows (signals a memleak), I save...
hello, have you solved this problem? it seems that there are three RegionType in https://nvidia.github.io/MinkowskiEngine/common.html i want to know if i use `dim=3`, i do not need use `RegionType=HYBRID`? `HYBRID`...
i think maybe you can get raw resolution by API : https://github.com/NVIDIA/MinkowskiEngine/blob/b975751d89732bf8048418770b349489baca864a/MinkowskiEngine/utils/quantization.py#L192