Sakura

python setup.py bdist_wheel出现错误

1

我使用的是ubuntu20.04+cuda11.3+cudnn8.2.1+torch1.12.1+spconv-cuda11.3的版本是2.3.6，cmake版本为3.28.0，在运行1 python setup.py bdist_wheel时候报错 Found cuDNN: v? (include: /usr/local/cuda-11.3/include, library: /usr/local/cuda-11.3/lib64/libcudnn.so) CMake Error at /home/ws/miniconda3/envs/hais/lib/python3.7/site-packages/torch/share/cmake/Caffe2/public/cuda.cmake:185 (message): PyTorch requires cuDNN 7 and above. Call Stack (most recent call first): /home/ws/miniconda3/envs/hais/lib/python3.7/site-packages/torch/share/cmake/Caffe2/Caffe2Config.cmake:88 (include)...

2024-05-13 15:45:01,062 - INFO - Save at: ./work_dirs/stpls3d/isbnet_backbone_stpls3d/ws 2024-05-13 15:45:03,147 - INFO - Total params: 7532252 2024-05-13 15:45:03,147 - INFO - Trainable params: 7532252 2024-05-13 15:45:03,151 - INFO - Load...

Thanks for your great work. I tried to train with my own data, the data I dropped into the network is in the format of xyzrgb semantic labels as well...

help

5

@ngoductuanlhp,Hello Professor, thank you for your great work. I would like to ask you if you think the work can be better applied in mono wood segmentation, I have some...

Hello and thanks for your great work. I have observed that you have created a new file in ISBNet/dataset/stpls3d /prepare_data_inst_instance_stpls3d.py file did not divide the test set for the stpls3d...

help

2

@ngoductuanlhp ngoductuanlhp Hello Professor, I have trained and got the model, my input raw data contains xyzrgb semantic labels and instance labels, now I want to test it on unlabeled...

how to train my own dataset?

1

Thanks for your great work! I have some questions for you, I noticed that the format of the for-instance dataset is: x,y,z,intensity,semantic_seg,treeID, if I want to train my own data,...

error

1

Thanks for your great work! I have some questions for you, I have trained to get a model when reproducing the npm3d dataset, but the problem in the picture occurs...

About SIBR_gaussianViewer

4

I have thanked you for your great work, I have tried to complete the training on Tanks and Temples Dataset, but when I visualise using SIBR_gaussianViewer_app.exe the following problem occurs:...