Cylinder3D
Cylinder3D copied to clipboard
xinge008
Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)
Traceback (most recent call last): File "train_cylinder_asym.py", line 167, in main(args) File "train_cylinder_asym.py", line 132, in main outputs = my_model(train_pt_fea_ten, train_vox_ten, train_batch_size) File "/home/autowise/data_ssd/zhangrun/Cylinder3D/conda_envs/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input,...
``` Step 33/40 : RUN python3 setup.py bdist_wheel ---> Running in 85988ff802dd running bdist_wheel running build running build_py creating build creating build/lib.linux-x86_64-3.6 creating build/lib.linux-x86_64-3.6/spconv copying spconv/__init__.py -> build/lib.linux-x86_64-3.6/spconv copying spconv/test_utils.py...
Thank you for your excellent work! When I run demo_folder.py to predict my own dataset (velodyne 64E, same as semanticKITTI), I find that the semantic labels generated by the pre-trained...
Hello, I have a question about the Pointnet that generates the Cylinder features. Is there any particular reason why the input tensor has the dimension (N, 9) not (N, 3)?...
This pull request is just so this fork shows up linked to original repository, and does not need to be merged. I have retained with Spconv 2.1.21, with slightly lower...
I used spconv 2.1.6 and make necessary changes refered in [link](https://github.com/traveller59/spconv/blob/master/docs/SPCONV_2_BREAKING_CHANGEs.md). However, an error occured in SubMConv3d in conv3x3 in segmentator_3d_asymm_spconv.py. The detailed error information is as below: > train_cylinder_asym.py...
python demo_folder.py --demo-folder model_load_dir --save-folder results demo_folder.py --demo-folder model_load_dir --save-folder results Namespace(config_path='config/semantickitti.yaml', demo_folder='model_load_dir', demo_label_folder='', save_folder='results') [480 360 32] matched parameter sets: 226, and no matched: 48 Traceback (most recent call...
Hi... I am following the following steps to get spconv set up. But the spconv wheel building is failing continuously since last 24 hours despite trying many options. What is...
After reading your code, it seems that you don't use circular_pad in the conv operation, which doesn't seem to make sense intuitively, won't this affect the model?
