optimizer.step() Not updating Model Weights/Parameters

autograd
1

I’m currently working on a solution via PyTorch. I’m not going to share the exact solution but I will provide code that reproduces the issue I’m having.

I have a model defined as follows:

class Net(nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        self.fc1 = nn.Linear(10,4)

    def foward(self,x):
        return nn.functional.relu(self.fc1(x))

Then I create a instance: my_model = Net(). Next I create an Adam optimizer as such:

optim = Adam(my_model.parameters())

# create a random input
inputs = torch.tensor(np.array([1,1,1,1,1,2,2,2,2,2]),dtype=torch.float32,requires_grad=True)

# get the outputs
outputs = my_model(inputs)

# compute gradients / backprop via
outputs.backward(gradient=torch.tensor([1.,1.,1.,5.]))

# store parameters before optimizer step
before_step = list(my_model.parameters())[0].detach().numpy()

# update parameters via
optim.step()

# collect parameters again
after_step = list(my_model.parameters())[0].detach().numpy()

# Print if parameters are the same or not
print(np.array_equal(before_step,after_step)) # Prints True

I provided my models parameters to the Adam optimizer, so I’m not exactly sure why the parameters aren’t updating. I know in most cases one uses a loss function, however I cannot do that in my case but I assumed if I specified model paramters to the optimizers, it would know to connect the two.

Anyone know why the parameters aren’t getting updated?

2

You need to .clone() the parameters as otherwise you would still compare the references.

3

how exactly should we use it? my model also does not update its parameters once load it, always has an error (optim.step() needs args and kwargs)

4

Could you post the full stacktrace and a minimal and executable code snippet to reproduce the issue?

5

of course, here you are.

error
error1237×987 223 KB

6

torch.optim.Adam does not require any input arguments to its step method:

model = nn.Linear(1, 1)
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)

model(torch.randn(1, 1)).mean().backward()
optimizer.step()

so I guess you might be using another implementation?