KPConv-PyTorch icon indicating copy to clipboard operation
KPConv-PyTorch copied to clipboard

An error occurred while running train_S3DIS.py data preparation!

Open yaoxingzhi opened this issue 3 years ago • 5 comments

Hi THOMAS!thank you for your contribution!

I met an error while running train_S3DIS as following:

(pytorch) nky@nky-System-Product-Name:~/PycharmProjects/KPConv-pytorch$ python3 train_S3DIS.py

Data Preparation


Preparing ply files Cloud Area_5 - Room 1/68 : conferenceRoom_2 Cloud Area_5 - Room 2/68 : office_23 Cloud Area_5 - Room 3/68 : office_29 Cloud Area_5 - Room 4/68 : office_12 Cloud Area_5 - Room 5/68 : office_20 Cloud Area_5 - Room 6/68 : office_10 Cloud Area_5 - Room 7/68 : office_41 Cloud Area_5 - Room 8/68 : office_33 Cloud Area_5 - Room 9/68 : pantry_1 Cloud Area_5 - Room 10/68 : hallway_14 Cloud Area_5 - Room 11/68 : hallway_2 Cloud Area_5 - Room 12/68 : hallway_8 Cloud Area_5 - Room 13/68 : office_30 Cloud Area_5 - Room 14/68 : office_25 Cloud Area_5 - Room 15/68 : office_11 Cloud Area_5 - Room 16/68 : office_5 Cloud Area_5 - Room 17/68 : office_14 Cloud Area_5 - Room 18/68 : office_19 Cloud Area_5 - Room 19/68 : hallway_10 Cloud Area_5 - Room 20/68 : office_26 Cloud Area_5 - Room 21/68 : office_4 Cloud Area_5 - Room 22/68 : storage_1 Cloud Area_5 - Room 23/68 : office_24 Cloud Area_5 - Room 24/68 : office_17 Cloud Area_5 - Room 25/68 : conferenceRoom_3 Cloud Area_5 - Room 26/68 : office_15 Cloud Area_5 - Room 27/68 : office_9 Cloud Area_5 - Room 28/68 : office_31 Cloud Area_5 - Room 29/68 : WC_1 Cloud Area_5 - Room 30/68 : office_16 Cloud Area_5 - Room 31/68 : hallway_11 Cloud Area_5 - Room 32/68 : WC_2 Cloud Area_5 - Room 33/68 : office_7 Cloud Area_5 - Room 34/68 : office_38 Cloud Area_5 - Room 35/68 : office_40 Cloud Area_5 - Room 36/68 : hallway_13 Cloud Area_5 - Room 37/68 : hallway_6 Traceback (most recent call last): File "/home/nky/PycharmProjects/KPConv-pytorch/train_S3DIS.py", line 271, in training_dataset = S3DISDataset(config, set='training', use_potentials=True) File "/home/nky/PycharmProjects/KPConv-pytorch/datasets/S3DIS.py", line 135, in init self.prepare_S3DIS_ply() File "/home/nky/PycharmProjects/KPConv-pytorch/datasets/S3DIS.py", line 700, in prepare_S3DIS_ply object_data = np.loadtxt(object_file, dtype=np.float32) File "/home/nky/anaconda3/envs/pytorch/lib/python3.9/site-packages/numpy/lib/npyio.py", line 1318, in loadtxt arr = _read(fname, dtype=dtype, comment=comment, delimiter=delimiter, File "/home/nky/anaconda3/envs/pytorch/lib/python3.9/site-packages/numpy/lib/npyio.py", line 979, in _read arr = _load_from_filelike( ValueError: the number of columns changed from 6 to 5 at row 180389; use usecols to select a subset and avoid this error

I have no idea how to solve this problem.I would be grateful if you could help me with this problem.

Best regards!

yaoxingzhi avatar Nov 02 '22 03:11 yaoxingzhi

Check you files, there might be an error in them and you will need to download the dataset again

HuguesTHOMAS avatar Nov 02 '22 12:11 HuguesTHOMAS

Check you files, there might be an error in them and you will need to download the dataset again

thank you, but it`s that OK about dataset? I use S3DIS Aligned Version

yaoxingzhi avatar Nov 03 '22 01:11 yaoxingzhi

I downloaded the dataset again and completed the training and testing, but there was a problem.

Open the Area_ 5. ply under the test result folder, the color displayed is only white, and different colors of different categories cannot be seen.

How can I solve this problem?

Thank you!Best regards!

yaoxingzhi avatar Nov 07 '22 01:11 yaoxingzhi

Cloud Area_5 - Room 5/68 : office_15 Cloud Area_5 - Room 6/68 : office_31 Cloud Area_5 - Room 7/68 : office_33 Cloud Area_5 - Room 8/68 : office_9 Cloud Area_5 - Room 9/68 : hallway_8 Cloud Area_5 - Room 10/68 : office_32 Cloud Area_5 - Room 11/68 : hallway_4 Cloud Area_5 - Room 12/68 : conferenceRoom_2 Cloud Area_5 - Room 13/68 : hallway_6 Traceback (most recent call last): File "train_S3DIS.py", line 271, in <module> training_dataset = S3DISDataset(config, set='training', use_potentials=True) File "/home/shi/mycode/KPConv-PyTorch/datasets/S3DIS.py", line 134, in __init__ self.prepare_S3DIS_ply() File "/home/shi/mycode/KPConv-PyTorch/datasets/S3DIS.py", line 699, in prepare_S3DIS_ply object_data = np.loadtxt(object_file, dtype=np.float32) File "/home/shi/miniconda3/envs/kpconv/lib/python3.8/site-packages/numpy/lib/npyio.py", line 1318, in loadtxt arr = _read(fname, dtype=dtype, comment=comment, delimiter=delimiter, File "/home/shi/miniconda3/envs/kpconv/lib/python3.8/site-packages/numpy/lib/npyio.py", line 979, in _read arr = _load_from_filelike( ValueError: the number of columns changed from 6 to 5 at row 180389; use usecols to select a subset and avoid this error I met the same error. How can I solve it?

Stone-sy avatar Dec 01 '22 12:12 Stone-sy

There may be a problem with the S3DIS dataset, you can try to re-download the dataset, I did it and was able to run.

Cloud Area_5 - Room 5/68 : office_15 Cloud Area_5 - Room 6/68 : office_31 Cloud Area_5 - Room 7/68 : office_33 Cloud Area_5 - Room 8/68 : office_9 Cloud Area_5 - Room 9/68 : hallway_8 Cloud Area_5 - Room 10/68 : office_32 Cloud Area_5 - Room 11/68 : hallway_4 Cloud Area_5 - Room 12/68 : conferenceRoom_2 Cloud Area_5 - Room 13/68 : hallway_6 Traceback (most recent call last): File "train_S3DIS.py", line 271, in <module> training_dataset = S3DISDataset(config, set='training', use_potentials=True) File "/home/shi/mycode/KPConv-PyTorch/datasets/S3DIS.py", line 134, in __init__ self.prepare_S3DIS_ply() File "/home/shi/mycode/KPConv-PyTorch/datasets/S3DIS.py", line 699, in prepare_S3DIS_ply object_data = np.loadtxt(object_file, dtype=np.float32) File "/home/shi/miniconda3/envs/kpconv/lib/python3.8/site-packages/numpy/lib/npyio.py", line 1318, in loadtxt arr = _read(fname, dtype=dtype, comment=comment, delimiter=delimiter, File "/home/shi/miniconda3/envs/kpconv/lib/python3.8/site-packages/numpy/lib/npyio.py", line 979, in _read arr = _load_from_filelike( ValueError: the number of columns changed from 6 to 5 at row 180389; use usecols to select a subset and avoid this error I met the same error. How can I solve it?

yaoxingzhi avatar Dec 01 '22 14:12 yaoxingzhi