Failed submission ¶
By: juseonghan on Sept. 11, 2023, 6:36 p.m.
Hello, I'm from Maplelab and I would like to know the reason for the failure of my preliminary submission. Thank you!
By: juseonghan on Sept. 11, 2023, 6:36 p.m.
Hello, I'm from Maplelab and I would like to know the reason for the failure of my preliminary submission. Thank you!
By: aneeqzia_isi on Sept. 11, 2023, 7:27 p.m.
Hi juseonghan,
Following are the logs for your failed submission:
Stdout 2023-09-11T18:34:14.838000+00:00 File found: /input/endoscopic-robotic-surgery-video.mp4 2023-09-11T18:34:14.838000+00:00 Video file to be loaded: /input/endoscopic-robotic-surgery-video.mp4
Stderr
2023-09-11T18:34:09.831000+00:00 /opt/conda/lib/python3.10/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
2023-09-11T18:34:09.831000+00:00 warnings.warn(
2023-09-11T18:34:09.831000+00:00 /opt/conda/lib/python3.10/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None
for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=None
.
2023-09-11T18:34:09.831000+00:00 warnings.warn(msg)
2023-09-11T18:34:14.833000+00:00 Could not find an int in the string 'endoscopic-robotic-surgery-video'.
2023-09-11T18:34:14.833000+00:00 Traceback (most recent call last):
2023-09-11T18:34:14.833000+00:00 File "/opt/conda/lib/python3.10/runpy.py", line 196, in _run_module_as_main
2023-09-11T18:34:14.836000+00:00 return _run_code(code, main_globals, None,
2023-09-11T18:34:14.837000+00:00 File "/opt/conda/lib/python3.10/runpy.py", line 86, in _run_code
2023-09-11T18:34:14.837000+00:00 exec(code, run_globals)
2023-09-11T18:34:14.837000+00:00 File "/opt/algorithm/process.py", line 294, in
2023-09-11T18:34:14.837000+00:00 Surgtoolloc_det().process()
2023-09-11T18:34:14.837000+00:00 File "/home/algorithm/.local/lib/python3.10/site-packages/evalutils/evalutils.py", line 183, in process
2023-09-11T18:34:14.837000+00:00 self.process_cases()
2023-09-11T18:34:14.837000+00:00 File "/home/algorithm/.local/lib/python3.10/site-packages/evalutils/evalutils.py", line 191, in process_cases
2023-09-11T18:34:14.837000+00:00 self._case_results.append(self.process_case(idx=idx, case=case))
2023-09-11T18:34:14.837000+00:00 File "/opt/algorithm/process.py", line 120, in process_case
2023-09-11T18:34:14.837000+00:00 scored_candidates = self.predict(case.path) #video file > load evalutils.py
2023-09-11T18:34:14.837000+00:00 File "/opt/algorithm/process.py", line 189, in predict
2023-09-11T18:34:14.837000+00:00 outputs = self.binary_seg_model(input_image)
2023-09-11T18:34:14.837000+00:00 File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
2023-09-11T18:34:14.837000+00:00 return forward_call(args, kwargs)
2023-09-11T18:34:14.837000+00:00 File "/opt/algorithm/models.py", line 85, in forward
2023-09-11T18:34:14.837000+00:00 conv1 = self.conv1(x)
2023-09-11T18:34:14.837000+00:00 File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
2023-09-11T18:34:14.837000+00:00 return forward_call(args, kwargs)
2023-09-11T18:34:14.837000+00:00 File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/container.py", line 217, in forward
2023-09-11T18:34:14.837000+00:00 input = module(input)
2023-09-11T18:34:14.838000+00:00 File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
2023-09-11T18:34:14.838000+00:00 return forward_call(*args, kwargs)
2023-09-11T18:34:14.838000+00:00 File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 463, in forward
2023-09-11T18:34:14.838000+00:00 return self._conv_forward(input, self.weight, self.bias)
2023-09-11T18:34:14.838000+00:00 File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 459, in _conv_forward
2023-09-11T18:34:14.838000+00:00 return F.conv2d(input, weight, bias, self.stride,
2023-09-11T18:34:14.838000+00:00 RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same
By: juseonghan on Sept. 11, 2023, 9:26 p.m.
Hello,
Thank you for the prompt response. Could you check the error log for my recent submission, titled "trial2"? Thank you.
By: juseonghan on Sept. 11, 2023, 9:28 p.m.
Never mind, I found the error for trial2.
By: juseonghan on Sept. 11, 2023, 10 p.m.
Hi, can you let me know the error logs for trial3? Thank you!
By: aneeqzia_isi on Sept. 12, 2023, 10:53 p.m.
Please see the logs below for the trial3 failed submission:
Stdout 2023-09-11T21:58:52.710000+00:00 File found: /input/endoscopic-robotic-surgery-video.mp4 2023-09-11T21:58:52.710000+00:00 Video file to be loaded: /input/endoscopic-robotic-surgery-video.mp4
Stderr
2023-09-11T21:57:05.683000+00:00 /opt/conda/lib/python3.10/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
2023-09-11T21:57:05.683000+00:00 warnings.warn(
2023-09-11T21:57:05.683000+00:00 /opt/conda/lib/python3.10/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None
for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=None
.
2023-09-11T21:57:05.683000+00:00 warnings.warn(msg)
2023-09-11T21:57:10.686000+00:00 Could not find an int in the string 'endoscopic-robotic-surgery-video'.
By: juseonghan on Sept. 13, 2023, 3:22 p.m.
Hello,
I'm unsure how to debug this, as it seems like it's an error that came from the test script to evaluate our algorithm. I'm looking over the format of my output, and it seems to be in line with the expected format. Could you give any guidance on this? Thank you.
By: aneeqzia_isi on Sept. 13, 2023, 6:31 p.m.
Are you basing your container on the example provided at https://github.com/aneeqzia-isi/surgtoolloc2022-category-2?
By: juseonghan on Sept. 13, 2023, 6:48 p.m.
Hello,
Yes, I simply cloned from that repository and changed process.py according to the instructions, and a few lines into the Dockerfile to include my pretrained models and utils.py.
By: juseonghan on Sept. 14, 2023, 3:41 p.m.
Hi just wanted to follow up - do you have any idea on how I could debug this? Sorry for the inconvenience.