assertion error when validating

[yxchng]

File "/home/user/conda/envs/pointmamba/lib/python3.10/site-packages/ocnn/octree/points.py", line 59, in check_input
    assert self.labels.dim() == 2

[Aristo23333]

File "/home/user/conda/envs/pointmamba/lib/python3.10/site-packages/ocnn/octree/points.py", line 59, in check_input
    assert self.labels.dim() == 2

Sorry since I haven't encountered this issue, so I don't understand the specific reason for this error. You could try to check and provide the code and instructions you use, especially the parts of the main code that are corresponding to the error.

[xuefanliu]

File "/home/user/conda/envs/pointmamba/lib/python3.10/site-packages/ocnn/octree/points.py", line 59, in check_input
    assert self.labels.dim() == 2

Sorry since I haven't encountered this issue, so I don't understand the specific reason for this error. You could try to check and provide the code and instructions you use, especially the parts of the main code that are corresponding to the error.

Hi authors! I also encounter this issue.

Traceback (most recent call last):
  File "/home/lxf/Workspace/Science/PointMamba/segmentation.py", line 184, in <module>
    SegSolver.main()
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/thsolver/solver.py", line 433, in main
    cls.worker(0, FLAGS)
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/thsolver/solver.py", line 422, in worker
    the_solver.run()
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/thsolver/solver.py", line 397, in run
    eval('self.%s()' % self.FLAGS.SOLVER.run)
  File "<string>", line 1, in <module>
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/thsolver/solver.py", line 320, in train
    self.train_epoch(epoch)
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/thsolver/solver.py", line 149, in train_epoch
    batch = next(self.train_iter)
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 630, in __next__
    data = self._next_data()
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1345, in _next_data
    return self._process_data(data)
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1371, in _process_data
    data.reraise()
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/_utils.py", line 694, in reraise
    raise exception
AssertionError: Caught AssertionError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 51, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/thsolver/dataset.py", line 44, in __getitem__
    output = self.transform(sample, idx)    # data augmentation + build octree
  File "/home/lxf/Workspace/Science/PointMamba/datasets/scannet.py", line 142, in __call__
    points = Points(torch.from_numpy(xyz), torch.from_numpy(sample['normals']),
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/ocnn/octree/points.py", line 45, in __init__
    self.check_input()
  File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/ocnn/octree/points.py", line 59, in check_input
    assert self.labels.dim() == 2
AssertionError

It seems like there's an issue with code in scannet.py

 points = Points(torch.from_numpy(xyz), torch.from_numpy(sample['normals']),
                    torch.from_numpy(color), torch.from_numpy(sample['labels']))

and in ocnn/octree/points.py

    if self.labels is not None:
      assert self.labels.dim() == 2
      assert self.labels.size(0) == self.points.size(0)

I print labels shape and get: Labels shape: torch.Size([237360]). Is this correct shape of labels?
And why does OCNN require the dimension of labels to be 2?

[Aristo23333]

Hello! I check out the dimension of my point label, it is actually the dimension is one.And in my ocnn/octree/points.py there isn't the dimension assertion. I will attach my dimension results as well as the points.py

----- 原始邮件 ----- 发件人: "xuefanliu" ***@***.***> 收件人: "IRMVLab/Point-Mamba" ***@***.***> 抄送: "RuiJi Yu" ***@***.***>, "Comment" ***@***.***> 发送时间: 星期二, 2024年 5 月 28日 上午 2:36:28 主题: Re: [IRMVLab/Point-Mamba] assertion error when validating (Issue #11)

> ``` > File "/home/user/conda/envs/pointmamba/lib/python3.10/site-packages/ocnn/octree/points.py", line 59, in check_input > assert self.labels.dim() == 2 > ``` Sorry since I haven't encountered this issue, so I don't understand the specific reason for this error. You could try to check and provide the code and instructions you use, especially the parts of the main code that are corresponding to the error.

Hi authors! I also encounter this issue. ``` Traceback (most recent call last): File "/home/lxf/Workspace/Science/PointMamba/segmentation.py", line 184, in <module> SegSolver.main() File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/thsolver/solver.py", line 433, in main cls.worker(0, FLAGS) File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/thsolver/solver.py", line 422, in worker the_solver.run() File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/thsolver/solver.py", line 397, in run eval('self.%s()' % self.FLAGS.SOLVER.run) File "<string>", line 1, in <module> File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/thsolver/solver.py", line 320, in train self.train_epoch(epoch) File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/thsolver/solver.py", line 149, in train_epoch batch = next(self.train_iter) File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 630, in __next__ data = self._next_data() File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1345, in _next_data return self._process_data(data) File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1371, in _process_data data.reraise() File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/_utils.py", line 694, in reraise raise exception AssertionError: Caught AssertionError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop data = fetcher.fetch(index) File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 51, in <listcomp> data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/thsolver/dataset.py", line 44, in __getitem__ output = self.transform(sample, idx) # data augmentation + build octree File "/home/lxf/Workspace/Science/PointMamba/datasets/scannet.py", line 142, in __call__ points = Points(torch.from_numpy(xyz), torch.from_numpy(sample['normals']), File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/ocnn/octree/points.py", line 45, in __init__ self.check_input() File "/home/lxf/anaconda3/envs/pointmamba/lib/python3.10/site-packages/ocnn/octree/points.py", line 59, in check_input assert self.labels.dim() == 2 AssertionError ``` It seems like there's an issue with code in scannet.py ``` points = Points(torch.from_numpy(xyz), torch.from_numpy(sample['normals']), torch.from_numpy(color), torch.from_numpy(sample['labels'])) ``` and in ocnn/octree/points.py ``` if self.labels is not None: assert self.labels.dim() == 2 assert self.labels.size(0) == self.points.size(0) ``` I print labels shape and get: `Labels shape: torch.Size([237360])`. Is this correct shape of labels? And why does OCNN require the dimension of labels to be 2?

…

-- Reply to this email directly or view it on GitHub: #11 (comment) You are receiving this because you commented. Message ID: ***@***.***>

[yxchng]

what is the version of your ocnn? current version has assertion, https://github.com/octree-nn/ocnn-pytorch/blob/master/ocnn/octree/points.py#L59

[xuefanliu]

Hello! I check out the dimension of my point label, it is actually the dimension is one.And in my ocnn/octree/points.py there isn't the dimension assertion. I will attach my dimension results as well as the points.py

Hi authors! Thanks for your reply! I change the OCNN version to 2.2.0 and solve the issue. Perhaps the OCNN version can be specified in requirements.txt so that the dimension of labels does not need to be changed.

[Aristo23333]

Thanks for your advice, I will specify the ocnn version in requirement.txt later, thank you!

----- 原始邮件 ----- 发件人: "xuefanliu" ***@***.***> 收件人: "IRMVLab/Point-Mamba" ***@***.***> 抄送: "RuiJi Yu" ***@***.***>, "Comment" ***@***.***> 发送时间: 星期三, 2024年 5 月 29日 下午 7:11:41 主题: Re: [IRMVLab/Point-Mamba] assertion error when validating (Issue #11)

Hello! I check out the dimension of my point label, it is actually the dimension is one.And in my ocnn/octree/points.py there isn't the dimension assertion. I will attach my dimension results as well as the points.py

Hi authors! Thanks for your reply! I change the OCNN version to 2.2.0 and solve the issue. Perhaps the OCNN version can be specified in requirements.txt so that the dimension of labels does not need to be changed.

…

-- Reply to this email directly or view it on GitHub: #11 (comment) You are receiving this because you commented. Message ID: ***@***.***>