ramdrop

Hi, Thank you for open sourcing your code. Could you please provide pre-trained models on the 3DMatch dataset, so that I can have a quick evaluation of SpinNet on other...

@wu-zhonghua Hi, do you have any idea how to solve this issue https://github.com/chrischoy/SpatioTemporalSegmentation/issues/51#issue-927950846 when adapting to v0.5? Many thanks if you could help.

Still an issue in 0.15.2: ```python import logging print(logging.getLogger().handlers) # > [] import opend3d print(logging.getLogger().handlers) # > [] ```

@shanhuhaifeng I met the same issue, could you share how to solve it?

No problem. I tried the first command (train MS-SVConv with one head) ``` poetry run python train.py task=registration models=registration/ms_svconv_base model_name=MS_SVCONV_B2cm_X2_1head data=registration/fragment3dmatch_sparse training=sparse_fragment_reg tracker_options.make_submission=True training.epochs=20 eval_frequency=10 ``` but the training results...

Many thanks for your additional information. With your conf file https://github.com/humanpose1/MS-SVConv/issues/21#issuecomment-1114220016, I trained MS-SVConv with one head using the command: ` poetry run python train.py task=registration models=registration/ms_svconv_base model_name=MS_SVCONV_B2cm_X2_1head data=registration/fragment3dmatch_sparse training=sparse_fragment_reg...

Thanks for your generated dataset. I have not managed to solve this issue but I found a workaround: split the raw directory list and run it multiple times to preprocess...

Sorry to bother you again, but I found my training results extremely weird: almost zero feature_matching_recall on both val and test dataset after 50 epochs. I suspect this could result...

Hi, sorry for the late reply. All variables in Eq.(1) are defined in the radar frame, i.e., the sensor coordinate system. Please refer to the figure in [27] for further...