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
It's not my priority right now (I am currently working on RNN layers).
If I understand inception layer, it is a maxout + conv 1x1 + conv 3x3 + conv 5x5 on the same input and then concatenated into one tensor on the depth dimension.
Forward pass should be achievable but I am not so sure how to make the error flow on the backward pass.
Since I don't have immediate use of such layer, I'm hoping someone will do PR for this kind of layers :)
Are you thinking in adding Inception Layers?
The text was updated successfully, but these errors were encountered: