Unexpected `shape` issue in Hessian-Vector computation about pyhessian HOT 4 OPEN

Hi, I have faced the same issue. Have you solved this issue?

from pyhessian.

@liujingcs Ah! It has been a long while. I think I upgraded the PyTorch version (probably 1.8).

If nothing works, you may want to check out this work by the same group: https://github.com/noahgolmant/pytorch-hessian-eigenthings

from pyhessian.

Hi, I have faced the same issue. Have you solved this issue?

Hi, I wonder if you have solved this issue. Thanks so much.

from pyhessian.

Hi guys, I meet the same issue and just figure it out. In my case, it's because there are some layers that have been defined in the model but didn't participate in forward or backward propagation. The issue was fixed after I delete the unused layers.
Another way to resolve it is modifying the get_params_grad function in the utils of pyhessian library. When the grade is None, the grads should be a Tensor of zeros instead of float zeros.

from pyhessian.