RuntimeError:
Module ‘Derivative’ has no attribute ‘gradient_dict’ (This attribute exists on the Python module, but we failed to convert Python type: ‘dict’ to a TorchScript type. Dictionary inputs must have entries. Its type was inferred; try adding a type annotation for the attribute.):
File “/modulus/modulus/eq/derivatives.py”, line 82
def forward(self, input_var: Dict[str, torch.Tensor]) → Dict[str, torch.Tensor]:
output_var = {}
for var_name, grad_sizes in self.gradient_dict.items():
~~~~~~~~~~~~~~~~~~ <— HERE
var = input_var[var_name]
grad_var = self.prepare_input(input_var, grad_sizes.keys())
while solving higher order equations getting thus error