You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Does it mean that in your implementation, you are not actually doing convolution over sequence? After reading the paper, I was left with an impression that you should project 4 latest inputs and then apply swish to obtain i and f. Sorry if I'm wrong as I don't really use PyTorch.
The text was updated successfully, but these errors were encountered:
From my understanding, we convolute over the entire sequence and not just the last 4 inputs. I'm sure there are many different ways to interpret the paper so I am open to discussing alternatives and trying them out.
Hello! Thank you for your implementation. However, I have a little question regarding the use of convolution.
Does it mean that in your implementation, you are not actually doing convolution over sequence? After reading the paper, I was left with an impression that you should project 4 latest inputs and then apply
swish
to obtaini
andf
. Sorry if I'm wrong as I don't really use PyTorch.The text was updated successfully, but these errors were encountered: