Question about a module that does not required grad

Thanks for the wonderful library!

I have one question about how to use higher.

I want to train the network with second order derivative,

but some parts of network (such as nn.Embedding ) are frozen.

something like this

net= Net()
param = filter(lambda x: x.requires_grad, model.parameters())
inner_opt = torch.optim.SGD(param, lr=1e-1)

with higher.innerloop_ctx(net, inner_opt, copy_initial_weights=False) as (fnet, diffopt):
  logits = net(batch_x)
  loss = loss_fnt(logits, batch_y)
  diffopt.step(loss)
              

but i got the error message “RuntimeError: One of the differentiated Tensors does not require grad”

[egrefen]

On my to-do list for tomorrow!

[egrefen]

Fixed in #11. Please re-open if this does not address your issue.