Optimizer type <class '__main__.HessianFree'> not supported by higher yet.

[jaytimbadia]

Hi,

I am trying this Hessian free optimization but it seems that I am not able to do as its throwing error saying -

Optimizer type <class 'main.HessianFree'> not supported by higher yet.

ValueError: Optimizer type <class '__main__.HessianFree'> not supported by higher yet.
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/tmp/ipykernel_41276/2741193226.py in <module>
      9 train_loader = torch.utils.data.DataLoader(train, batch_size=4, shuffle=False)
     10 
---> 11 with higher.innerloop_ctx(model, opti, track_higher_grads=False) as (fmodel, diffopt):
     12     for xs, ys in train_loader:
     13         logits = fmodel(xs)

/usr/lib/python3.8/contextlib.py in __enter__(self)
    111         del self.args, self.kwds, self.func
    112         try:
--> 113             return next(self.gen)
    114         except StopIteration:
    115             raise RuntimeError("generator didn't yield") from None

~/Desktop/Glacier/luck/lib/python3.8/site-packages/higher/__init__.py in innerloop_ctx(model, opt, device, copy_initial_weights, override, track_higher_grads)
     89         track_higher_grads=track_higher_grads
     90     )
---> 91     diffopt = optim.get_diff_optim(
     92         opt,
     93         model.parameters(),

~/Desktop/Glacier/luck/lib/python3.8/site-packages/higher/optim.py in get_diff_optim(opt, reference_params, fmodel, device, override, track_higher_grads, **kwargs)
    780         )
    781     else:
--> 782         raise ValueError(
    783             "Optimizer type {} not supported by higher yet.".format(type(opt))
    784         )

ValueError: Optimizer type <class '__main__.HessianFree'> not supported by higher yet.

Please Help!