I have a loss function defined like this def Loss(U,G_metric,p,q): ''' U is a function takes a vector and return a scalar G_metric is a function returns a matrix; it's a metric tensor p ,q are two vectors ''' D = p.size()[0] # get the dimension of p,q G = G_metric(q) # …

[image] ElleryL: x = Variable(x,requires_grad=True) G = torch.eye(2)*3 # compute matrix Here G does not have requires_grad=True. I think, thats the reason for the error. Probably, you wanted to do this: x = torch.Tensor([3]) x = Variable(x,requires_grad=True) G = torch.eye(2) * x # compute …

Compute gradient of determinant function or inverse function

autograd

Ranahanocka (Rana Hanocka) August 26, 2018, 3:15am 4

I’m not sure. According to this it’s not available:

Yet this PR looks like it might do it.

Did you try torch.inverse?