Hello,
I’m trying to implement the spatial weighting loss for the nonslip boundary condition in a Navier-Stokes problem. This is the code I’m using, interior_mesh
represents the surface of the domain of interest, which is a closed .stl mesh similar to the one in the aneurysm task.
# interior
interior = PointwiseInteriorConstraint(
nodes=nodes,
geometry=interior_mesh,
outvar={"continuity": 0,"momentum_x": 0, "momentum_y": 0, "momentum_z": 0},
batch_size=cfg.batch_size.interior,
param_ranges=time_range,
lambda_weighting={
"continuity": interior_mesh.sdf,
"momentum_x": interior_mesh.sdf,
"momentum_y": interior_mesh.sdf,
"momentum_z": interior_mesh.sdf,
},
)
domain.add_constraint(interior, "interior")
I keep getting the following error.
Error executing job with overrides: []
Traceback (most recent call last):
File "/modulus/examples/RT/code/fourflow.py", line 141, in run
continuity = PointwiseInteriorConstraint(
File "/opt/conda/lib/python3.8/site-packages/modulus-22.3-py3.8.egg/modulus/continuous/constraints/constraint.py", line 411, in __init__
lambda_weighting = _compute_lambda_weighting(
File "/opt/conda/lib/python3.8/site-packages/modulus-22.3-py3.8.egg/modulus/continuous/constraints/constraint.py", line 907, in _compute_lambda_weighting
computed_lambda_weighting[key] = np_lambdify(
File "/opt/conda/lib/python3.8/site-packages/modulus-22.3-py3.8.egg/modulus/sympy_utils/numpy_printer.py", line 144, in grouped_lambda
output.append(lambdify_f_i(**invar))
File "/opt/conda/lib/python3.8/site-packages/modulus-22.3-py3.8.egg/modulus/sympy_utils/numpy_printer.py", line 60, in lambdify_f_i
return f_i(**{key: x[key] for key in args})
File "/opt/conda/lib/python3.8/site-packages/modulus-22.3-py3.8.egg/modulus/sympy_utils/numpy_printer.py", line 60, in <dictcomp>
return f_i(**{key: x[key] for key in args})
KeyError: 'points'
Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.