yichaoshen-MS

Hi, I have finished the train and test in scannet200. However, when I attempt to submit the output in "eval_output/" to the official website of scannet, it recalled back that...

I found there is a 3-dims labels per point, first is the class-id, the second is instance-id, but I don't know the 3rd dim means. I guess it may be...

support multi-gpus ?

2

When I use multi-gpu by change the $gpus in config, I meet the error TypeError: cannot pickle 'MinkowskiConvolutionFunction' object

How to process the data for Scannet200?

1

I should preprocess scannet200 in this scannet200-original Repostitory(LanguageGroundedSemseg,https://github.com/RozDavid/LanguageGroundedSemseg) or the Repostitory（scannet :[https://github.com/ScanNet/ScanNet/blob/master/BenchmarkScripts/ScanNet200/preprocess_scannet200.py）](https://github.com/ScanNet/ScanNet/blob/master/BenchmarkScripts/ScanNet200/preprocess_scannet200.py%EF%BC%89)?

MinkowskiConvolutionFunction cannot support multi-gpu?

5

**Describe the bug** When use multi-gpu to train network by pytorch-lighting, it meets error may because "MinkowskiConvolutionFunction" can not pickle("TypeError: cannot pickle 'MinkowskiConvolutionFunction' object") What's more, I found this PR(https://github.com/NVIDIA/MinkowskiEngine/pull/139)...

Cannot set the "kThresh" and "segMinVerts" in /Segmentor tools?

1

I follow the operations in https://github.com/ScanNet/ScanNet/tree/master/Segmentator, however when I run the command like "./segmentator scene0707_00_vh_clean_2.ply [kThresh=0.01] [segMinVerts=20]", the "kThresh=0.000000, segMinVerts=0" always works, which means I cannot change the value of...

What is the difference between IsaacGymEnvs and OmniIsaacGymEnvs ？

3

https://github.com/NVIDIA-Omniverse/IsaacGymEnvs

What are the settings of the num_gpus and batchsize_per_gpu? And what is the total gpu number? Is support gradient_accumulation_steps?