edits for PINN/custom loss functions

[rmojgani]

How can I use the code for the case where I have a custom loss function, and not a torch.nn."LOSS"?
I'm specifically trying to reproduce the results in https://arxiv.org/abs/2109.01050 , and cannot get the PyHessian class to work.

Also, in the PINN case, network does not have a data=(inputs, targets), can I use the same code/class or I need further edits?

I'm thinking of changing the loss in line 92

PyHessian/pyhessian/hessian.py

Line 92 in 1a42737

loss = self.criterion(outputs, targets.to(device))

with my custom loss (from the network)

wondering if that's all the changes I need

---

PS:
Also since I'm only interested in the eigenvectors, tried to exctract parameters and gradients, i.e.,

PyHessian/pyhessian/utils.py

Line 61 in 1a42737

def get_params_grad(model):

and pass it to

PyHessian/pyhessian/hessian.py

Line 111 in 1a42737

def eigenvalues(self, maxIter=100, tol=1e-3, top_n=1):

Though it's throwing some error at me, would appreciate any insights,

`Traceback (most recent call last):

File "/tmp/ipykernel_709492/339026100.py", line 1, in
hv = torch.autograd.grad(gradsH,

File "/home/xxx/.local/lib/python3.8/site-packages/torch/autograd/init.py", line 229, in grad
grad_outputs_ = make_grads(outputs, grad_outputs)

File "/home/xxx/.local/lib/python3.8/site-packages/torch/autograd/init.py", line 33, in _make_grads
if not out.shape == grad.shape:

AttributeError: 'float' object has no attribute 'shape'`