Is it possible to do backward in this case?

vision
1

Let’s see an example with a simple architecture.

... -- conv1 -- conv2 -- ...

If the weights of the conv2 layer can be learned then it is possible to learn the weights of the conv1.
Now, let’s see another example with a similar architecture except adding tile function.

... -- conv1 -- tile -- conv2 -- ...

In this case, is it feasible to apply backpropagation algorithm to conv1 layer?
Thank you.

2

Hi,

If you’re tile function is differentiable, then yes. Could you give more details about that function?

3

An example for the function is torch.tile — PyTorch master documentation. Btw, I found this link Are all operations defined in torch.Tensor differentiable?. :smiley: