The algorithm failed on one or more cases.

The algorithm failed on one or more cases.  

  By: amrn on July 31, 2023, 10:51 a.m.

Created: July 31, 2023, 3:35 a.m PDT

can you please take a look. thanks

Re: The algorithm failed on one or more cases.  

  By: apepe on July 31, 2023, 10:54 a.m.

Hi,

Looks like a version issue

2023-07-31T10:43:14.863000+00:00 Traceback (most recent call last): 2023-07-31T10:43:14.863000+00:00 File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main 2023-07-31T10:43:14.863000+00:00 return _run_code(code, main_globals, None, 2023-07-31T10:43:14.863000+00:00 File "/usr/lib/python3.10/runpy.py", line 86, in _run_code 2023-07-31T10:43:14.863000+00:00 exec(code, run_globals) 2023-07-31T10:43:14.863000+00:00 File "/opt/app/process.py", line 228, in 2023-07-31T10:43:14.863000+00:00 Segaalgorithm().process() 2023-07-31T10:43:14.863000+00:00 File "/home/user/.local/lib/python3.10/site-packages/evalutils/evalutils.py", line 183, in process 2023-07-31T10:43:14.863000+00:00 self.process_cases() 2023-07-31T10:43:14.863000+00:00 File "/home/user/.local/lib/python3.10/site-packages/evalutils/evalutils.py", line 191, in process_cases 2023-07-31T10:43:14.863000+00:00 self._case_results.append(self.process_case(idx=idx, case=case)) 2023-07-31T10:43:14.863000+00:00 File "/opt/app/process.py", line 182, in process_case 2023-07-31T10:43:14.863000+00:00 result_meta_tensor = run_inference(image=im_meta_tensor) 2023-07-31T10:43:14.863000+00:00 File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context 2023-07-31T10:43:14.863000+00:00 return func(args, *kwargs) 2023-07-31T10:43:14.863000+00:00 File "/opt/app/process.py", line 96, in run_inference 2023-07-31T10:43:14.863000+00:00 data = batch_data["image"].as_subclass(torch.Tensor).to(memory_format=torch.channels_last_3d, device=device) 2023-07-31T10:43:14.863000+00:00 File "/usr/local/lib/python3.10/dist-packages/torch/cuda/init.py", line 264, in _lazy_init 2023-07-31T10:43:14.863000+00:00 torch._C._cuda_init() 2023-07-31T10:43:14.863000+00:00 RuntimeError: The NVIDIA driver on your system is too old (found version 11040). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver.

Re: The algorithm failed on one or more cases.  

  By: amrn on Aug. 4, 2023, 11:33 a.m.

Hi, can you please check the error for todays submission (aug4, phase2). It’s says failed …

Re: The algorithm failed on one or more cases.  

  By: apepe on Aug. 5, 2023, 7:08 a.m.

Hi

You had a "time limit exceeded" on your submission

Antonio