cea-list / kalicalib Goto Github PK

Hello,

I followed the instructions given in the challenge repository to set up the data. However, when I run train.py, I get the following error output:

0%| | 0/240 [00:00<?, ?it/s]
0%| | 0/240 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/sminam01/bball-tracking/KaliCalib/kalicalib/train.py", line 90, in
train(cfg)
File "/sminam01/bball-tracking/KaliCalib/kalicalib/train.py", line 54, in train
for imgs, data in pbar:
File "/sminam01/condaenv/Pipeline/lib/python3.12/site-packages/tqdm/std.py", line 1181, in iter
for obj in iterable:
File "/sminam01/condaenv/Pipeline/lib/python3.12/site-packages/torch/utils/data/dataloader.py", line 631, in next
data = self._next_data()
^^^^^^^^^^^^^^^^^
File "/sminam01/condaenv/Pipeline/lib/python3.12/site-packages/torch/utils/data/dataloader.py", line 1346, in _next_data
return self._process_data(data)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/sminam01/condaenv/Pipeline/lib/python3.12/site-packages/torch/utils/data/dataloader.py", line 1372, in _process_data
data.reraise()
File "/sminam01/condaenv/Pipeline/lib/python3.12/site-packages/torch/_utils.py", line 722, in reraise
raise exception
AssertionError: Caught AssertionError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/sminam01/condaenv/Pipeline/lib/python3.12/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
^^^^^^^^^^^^^^^^^^^^
File "/sminam01/condaenv/Pipeline/lib/python3.12/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
~~~~~~~~~~~~^^^^^
File "/sminam01/bball-tracking/KaliCalib/data/datasets/viewds.py", line 315, in getitem
item = self.vds.dataset.query_item(key)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/sminam01/condaenv/Pipeline/lib/python3.12/site-packages/aleatorpy/pseudo_random.py", line 70, in call
result = self.f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^
File "/sminam01/condaenv/Pipeline/lib/python3.12/site-packages/deepsport_utilities/utils.py", line 30, in query_item
item = self.parent.query_item(key)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/sminam01/condaenv/Pipeline/lib/python3.12/site-packages/mlworkflow/datasets.py", line 250, in query_item
item = transform(key, item)
^^^^^^^^^^^^^^^^^^^^
File "/sminam01/bball-tracking/KaliCalib/data/datasets/viewds.py", line 474, in call
item = self._apply_transform_once(key, item)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/sminam01/bball-tracking/KaliCalib/data/datasets/viewds.py", line 444, in _apply_transform_once
parameters = self._get_current_parameters(key, item)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/sminam01/condaenv/Pipeline/lib/python3.12/site-packages/deepsport_utilities/ds/instants_dataset/views_transforms.py", line 181, in _get_current_parameters
size = float(view.calib.compute_length2D(100, keypoints))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/sminam01/condaenv/Pipeline/lib/python3.12/site-packages/calib3d/calib.py", line 358, in compute_length2D
assert np.isscalar(length3D), f"This function expects a scalar length3D argument. Received {length3D}"
AssertionError: This function expects a scalar length3D argument. Received [[338.5422839 ]
[857.10081456]
[ 0. ]]

Any help would be appreciated! Thanks.