Backpropagate the loss of a certain layer

autograd
1

Hello all
How can I backpropagate loss over a specific layer of network (not the all the layers or the layers before the specific layer). I want to update the weights of a certain layer.
Thanks

2

You could pass the desired parameters as the inputs argument to the .backward() call, which would then accumulate the gradients only in these parameters and will ignore the rest.

4

I wonder if you would share with me any example code.

5

This should work:

model = models.resnet18()

x = torch.randn(2, 3, 224, 224)
out = model(x)
loss = out.mean()

loss.backward(inputs=list(model.conv1.parameters()))

for name, param in model.named_parameters():
    print(name, param.grad)
2 Likes