nnf_bilinear {torch} | R Documentation |
Bilinear
Description
Applies a bilinear transformation to the incoming data:
y=x1Ax2+b
Usage
nnf_bilinear(input1, input2, weight, bias = NULL)
Arguments
input1 |
(N,∗,Hin1) where Hin1=\mboxin1_features
and ∗ means any number of additional dimensions.
All but the last dimension of the inputs should be the same.
|
input2 |
(N,∗,Hin2) where Hin2=\mboxin2_features
|
weight |
(\mboxout_features,\mboxin1_features,\mboxin2_features)
|
bias |
(\mboxout_features)
|
Value
output (N,∗,Hout)
where Hout=\mboxout_features
and all but the last dimension are the same shape as the input.
[Package
torch version 0.13.0
Index]