optimizer.SGD(filter(lambda p: p.requires_grad, model.parameters()), lr=1e-3)

j = Variable(torch.randn(5,5), requires_grad=True)

m = nn.Linear(10,10)

for i in m.parameters():
  i.requires_grad=False

for p in self.parameters():
  p.requires_grad=False

class Net(nn.Module):
  def __init__(self):
    super(Net, self).__init__()
    self.conv1 = nn.Conv2d(1, 6, 5)
    self.conv2 = nn.Conv2d(6, 16, 5)

    for p in self.parameters():
      p.requires_grad=False

    self.fc1 = nn.Linear(16 * 5 * 5, 120)
    self.fc2 = nn.Linear(120, 84)
    self.fc3 = nn.Linear(84, 10)