Modulus example case (helmholtz): Value Error

[mitanshtrip]

I am running the /example/helmholtz/ case as described in the installation guide. The output/ folder is also created. however, I am getting an error as follows:

/examples/helmholtz# python3 helmholtz.py
[17:05:59] - JIT using the NVFuser TorchScript backend
[17:05:59] - JitManager: {‘_enabled’: True, ‘_arch_mode’: <JitArchMode.ONLY_ACTIVATION: 1>, ‘_use_nvfuser’: True, ‘_autograd_nodes’: False}
[17:05:59] - GraphManager: {‘_func_arch’: False, ‘_debug’: False, ‘_func_arch_allow_partial_hessian’: True}
Error executing job with overrides:
ValueError: could not convert string to float: ‘oid sha256:xxxx’

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File “helmholtz.py”, line 72, in run
openfoam_var = csv_to_dict(to_absolute_path(“validation/helmholtz.csv”), mapping)
File “/usr/local/lib/python3.8/dist-packages/modulus-22.9-py3.8.egg/modulus/utils/io/csv_rw.py”, line 33, in csv_to_dict
values = np.loadtxt(filename, skiprows=1, delimiter=delimiter, unpack=False)
File “/usr/local/lib/python3.8/dist-packages/numpy/lib/npyio.py”, line 1338, in loadtxt
arr = _read(fname, dtype=dtype, comment=comment, delimiter=delimiter,
File “/usr/local/lib/python3.8/dist-packages/numpy/lib/npyio.py”, line 999, in _read
arr = _load_from_filelike(
ValueError: could not convert string ‘oid sha256:xxxxxxxxxxxxx’ to float64 at row 0, column 1.

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.

[ngeneva]

Hi @mitanshtrip

This is an issue with not having Git LFS installed properly. Please see the following post or the warning box in our install notes:

Unable to run helmholtz.py after installing 22.03.1

Hi @yeokiwi , Looks like you don’t have Git LFS installed. We use Git LFS in our examples repo to store the data files, without LFS it will just be a pointer file. With Git LFS installed, try re-cloning the examples repo. That CSV file for LDC should now have proper data in it and the example should run. More information about Git LFS can be found here.

Let us know if your still having problems even with Git LFS installed. Thanks.

[mitanshtrip]

I was able to install it correctly. I am getting a different error now:

C:\Users\tripatmn.conda\envs\tfgpu\lib\site-packages\hydra_internal\callbacks.py:26: UserWarning: Callback ModulusCallback.on_job_start raised RuntimeError: Running CUDA fuser is only supported on CUDA builds.
warnings.warn(
Error executing job with overrides:
Traceback (most recent call last):
File “C:\Users\tripatmn\ModFiles\examples\helmholtz\helmholtz.py”, line 52, in run
interior = PointwiseInteriorConstraint(
File “C:\Users\tripatmn.conda\envs\tfgpu\lib\site-packages\modulus-22.9-py3.9.egg\modulus\domain\constraint\continuous.py”, line 493, in init
super().init(
File “C:\Users\tripatmn.conda\envs\tfgpu\lib\site-packages\modulus-22.9-py3.9.egg\modulus\domain\constraint\constraint.py”, line 55, in init
self.model = Graph(
File “C:\Users\tripatmn.conda\envs\tfgpu\lib\site-packages\modulus-22.9-py3.9.egg\modulus\graph.py”, line 141, in init
necessary_nodes[i] = FuncArch(
File “C:\Users\tripatmn.conda\envs\tfgpu\lib\site-packages\modulus-22.9-py3.9.egg\modulus\models\arch.py”, line 618, in init
I_N1 = torch.eye(out_features)[self.needed_output_dims]
IndexError: tensors used as indices must be long, byte or bool tensors

[ngeneva]

Seems theres something wrong with your bare metal installation. Please make sure all the required dependencies have been installed with the correct versions. I would then also try shutting off FuncTorch using following lines in your config.yaml for this problem:

graph:
  func_arch: false