python train.py --config config/softgroup_fold5_backbone_s3dis.yaml

[PengboLi1998]

Hi,excuse me .When I run the python train.py --config config/softgroup_fold5_backbone_s3dis.yaml. It throws the following error.Could you please help me ?

Traceback (most recent call last): File "train.py", line 218, in train_epoch(dataset.train_data_loader, model, model_fn, optimizer, epoch) File "train.py", line 48, in train_epoch for i, batch in enumerate(train_loader): File "/home/ketizu/anaconda3/envs/boge2/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 819, in next return self._process_data(data) File "/home/ketizu/anaconda3/envs/boge2/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 846, in _process_data data.reraise() File "/home/ketizu/anaconda3/envs/boge2/lib/python3.6/site-packages/torch/_utils.py", line 369, in reraise raise self.exc_type(msg) TypeError: init() missing 1 required positional argument: 'dtype'

[thangvubk]

I am not sure which causes this error. Please check your installation and data path.

[liujingangel]

have you solved this error？I met the same problem with my custom data.

[PengboLi1998]

have you solved this error？I met the same problem with my custom data.

hello,I was because the Spconv library was installed with the wrong version.