Hi everyone,
I’m new to the forums, so correct me if I have not framed the problem correctly.
I’m in a situation where I have to make a copy of a specific block of the network for some further calculations (like Jacobian)
My network looks like this:
class AutoCanonical(torch.nn.Module):
def __init__(self, d_in, d_hidden, d_out, activation_fn, device, experiment):
super(AutoCanonical, self).__init__()
self.layers = torch.nn.ModuleList()
## Block for converting provided coordinates to canonical coordinates
self.layer1 = torch.nn.Linear(d_in, 50)
self.layers.append(self.layer1)
self.layer2 = torch.nn.Linear(50, 50)
self.layers.append(self.layer2)
self.layer3 = torch.nn.Linear(50, d_in)
self.layers.append(self.layer3)
## -------------------------------------------------
## Hamiltonian block
self.layer4 = torch.nn.Linear(d_in, 200)
self.layers.append(self.layer4)
self.layer5 = torch.nn.Linear(200, 200)
self.layers.append(self.layer5)
self.layer6 = torch.nn.Linear(200, 1)
self.layers.append(self.layer6)
## -------------------------------------------------
def to_canonical(self, x):
y1 = self.nonlinear_fn(self.layer1(x))
y2 = self.nonlinear_fn(self.layer2(y1))
#out = self.nonlinear_fn(self.layer3(y2))
out = self.layer3(y2)
return out
def Ham(self, x):
y1 = self.nonlinear_fn(self.layer4(x))
y2 = self.nonlinear_fn(self.layer5(y1))
#nn_fn = torch.nn.LeakyReLU(0.9)
out = self.layer6(y2)
return out
def forward(self, x):
# set_trace()
can_coords = self.to_canonical(x) # convert to canonical variables
H = self.ham(can_coords)
return H
I would like to make a copy of self.to_canonical block and would like to use it calculate it’s jacobian. How do I make a copy of that ?