prbonn/segcontrast issues and pull requests

#20 - Question About Training Loss

Issue - State: closed - Opened by Cedric-Perauer 11 months ago - 5 comments

#19 - inference_vis.py -> ERROR: kernel must be CUDA.

Issue - State: closed - Opened by AbhishekKaushikCV about 1 year ago - 2 comments

#18 - In what part of the code ContrastiveLoss is used?

Issue - State: closed - Opened by Rezamh13 over 1 year ago - 5 comments

#17 - About the time cost of pre-training

Issue - State: closed - Opened by JUNJIE99 almost 2 years ago - 2 comments

#16 - Can segcontrast be implemented on S3DIS without changing a lot of code?

Issue - State: closed - Opened by SC-shendazt almost 2 years ago - 3 comments

#15 - Code for PointNet++

Issue - State: closed - Opened by barzanisar about 2 years ago - 3 comments

#14 - t

Issue - State: closed - Opened by nuneslu over 2 years ago

#13 - about the downstream task

Issue - State: closed - Opened by YanhaoWu over 2 years ago - 10 comments

#12 - about the GPU memory

Issue - State: closed - Opened by YanhaoWu over 2 years ago - 2 comments

#11 - RuntimeError: NCCL error in: /pytorch/torch/lib/c10d/ProcessGroupNCCL.cpp:31, unhandled cuda error, NCCL version 2.7.8

Issue - State: closed - Opened by YanhaoWu over 2 years ago - 4 comments

#10 - About MinkowskiEngine/utils/quantization.py

Issue - State: closed - Opened by volare1996 over 2 years ago - 24 comments

#9 - About comparative experiment

Issue - State: closed - Opened by YanhaoWu over 2 years ago - 4 comments

#8 - An error occurred while fine-tuning the model

Issue - State: closed - Opened by volare1996 over 2 years ago - 2 comments

#7 - question about why disable batch_shuffle_ddp

Issue - State: closed - Opened by jackmsye over 2 years ago - 1 comment

#6 - Question about the requirements.txt?

Issue - State: closed - Opened by volare1996 over 2 years ago - 1 comment

#5 - Is it feasible to apply this method to the Semantic3D dataset?