loicland / superpoint_graph

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
MIT License
745 stars 214 forks source link

Running on Stanford3dDataset_v1.2_Aligned_Version, the error occurs. #279

Closed whuhxb closed 1 year ago

whuhxb commented 1 year ago

Have you ever met this error when running partition.py? Thanks a lot.

Timer : 100.8 / 1031.9 / 806.3 6 / 23---> hallway_2 creating the feature file... Traceback (most recent call last): File "partition/partition.py", line 123, in xyz, rgb, labels = read_s3dis_format(data_file) File "/export/home/hanxiaobing/Documents/PlaneNet_PlaneRCNN/DGCNN_PointNet2/SensatUrban/SPG/superpoint_graph-release/partition/provider.py", line 163, in read_s3dis_format nn = NearestNeighbors(n_neighbors=2, radius=0.4).fit(xyz) # added by hxb File "/export/home/hanxiaobing/anaconda3/envs/SPG/lib/python3.7/site-packages/sklearn/neighbors/_unsupervised.py", line 166, in fit return self._fit(X) File "/export/home/hanxiaobing/anaconda3/envs/SPG/lib/python3.7/site-packages/sklearn/neighbors/_base.py", line 435, in _fit X = self._validate_data(X, accept_sparse="csr") File "/export/home/hanxiaobing/anaconda3/envs/SPG/lib/python3.7/site-packages/sklearn/base.py", line 566, in _validate_data X = check_array(X, **check_params) File "/export/home/hanxiaobing/anaconda3/envs/SPG/lib/python3.7/site-packages/sklearn/utils/validation.py", line 800, in check_array _assert_all_finite(array, allow_nan=force_all_finite == "allow-nan") File "/export/home/hanxiaobing/anaconda3/envs/SPG/lib/python3.7/site-packages/sklearn/utils/validation.py", line 116, in _assert_all_finite type_err, msg_dtype if msg_dtype is not None else X.dtype ValueError: Input contains NaN, infinity or a value too large for dtype('float32').

loicland commented 1 year ago

Did you apply the fix on S3DIS?

whuhxb commented 1 year ago

Did you apply the fix on S3DIS?

After conducting fix on S3DIS, the error still occurs.

Timer : 98.6 / 1019.4 / 794.3 6 / 23---> hallway_2 creating the feature file... Traceback (most recent call last): File "partition/partition.py", line 123, in xyz, rgb, labels = read_s3dis_format(data_file) File "/export/home/hanxiaobing/Documents/PlaneNet_PlaneRCNN/DGCNN_PointNet2/SensatUrban/SPG/superpoint_graph-release/partition/provider.py", line 155, in read_s3dis_format room_ver = genfromtxt(raw_path, delimiter=' ') File "/export/home/hanxiaobing/anaconda3/envs/SPG/lib/python3.7/site-packages/numpy/lib/npyio.py", line 2124, in genfromtxt raise ValueError(errmsg) ValueError: Some errors were detected ! Line #926337 (got 7 columns instead of 6)

Have you ever met this error? Thanks a lot.

loicland commented 1 year ago

maybe check line 926337 in your hallway_2 file, apparently there a missing character, you can fix it by hand.

whuhxb commented 1 year ago

maybe check line 926337 in your hallway_2 file, apparently there a missing character, you can fix it by hand.

which area?

loicland commented 1 year ago

the one with 23 rooms

whuhxb commented 1 year ago

926337

OK. Checked. Thanks.