Angelo
(Angelo Franciosini)
January 24, 2018, 10:41am
1
Hello everyone, I’m new to pyTorch.
Is there a way to define a deconvolution layer that takes its weights (conv. filters) from a previous convolutional layer?
In pseudo-code:
x=conv2d(W,x)
x=convTransponse2d(W.T,x)
For reference, I’m trying to implement this network:
http://ieeexplore.ieee.org/document/7962256/
1 Like
sonsang
(Sanghyun Son)
January 24, 2018, 10:51am
2
I think nn.functional will give you the answer.
Like
import torch.nn.functional as F
x = F.conv2d(x, W)
x = F.conv_transpose2d(x, W.t())
2 Likes
Angelo
(Angelo Franciosini)
January 24, 2018, 10:54am
3
Nice! Thanks for the fast reply