zhang-zihui
zhang-zihui
@narges-tk, Hi, seems the error occurred in MinkowskiEngine, did you keep the same virtual environment with us?
Hi, @narges-tk, I guess the MinkowskiEngine may have some errors, you can try another installation: Please install pytorch and other packages as illustrated in Readme. and activate the environment, then...
https://github.com/coqui-ai/TTS/issues/1517, this issue may provide some help, typing "unset LD_LIBRARY_PATH" in your python environment as https://github.com/coqui-ai/TTS/issues/1517#issuecomment-1437973294
Hi @ome-13, This error means the pfh is an empty list, but on the previous code, we search for all valid superpoints to compute pfh feature. So, can you check...
Hi, @narges-tk , We use a single 3090GPU to do all experiments, so it requires 24G cuda memory.
Hi, @ome-13, you can modify the evaluation code in eval_S3DIS.py, and also modify the dataloader function in https://github.com/vLAR-group/GrowSP/blob/b7eaece0847189c7b94854a03d7a3816bf478236/datasets/S3DIS.py#L208. I'm not clear your specific evaluation data, you may mimic my code...
Hi @zengxinran, please see the second step in running code, for example, on S3DIS, please second step of 2.1 "python data_prepare/initialSP_prepare_S3DIS.py"
hi @lrnb12345 , Could you provide some visualization examples for your personal data? For the region growing+vccs, you may try to set a larger threshold for normal distance on region...
@mooncakehub, we use an RTX3090 GPU with 24G memory.
@mooncakehub the training backbone SparseConv can be multi-GPU, but we didn't implement it, you may have a try.