torch (version 0.14.2)

nnf_bilinear: Bilinear

Description

Applies a bilinear transformation to the incoming data: $y=x_{1}A{x}_2+b$

Usage

nnf_bilinear(input1, input2, weight, bias = NULL)

Value

output $(N,\ast ,H_{out})$ where $H_{out}=\text{out\_features}$

and all but the last dimension are the same shape as the input.

Arguments

input1

$(N,\ast ,H_{in1})$ where $H_{in1}=\text{in1\_features}$ and $\ast$ means any number of additional dimensions. All but the last dimension of the inputs should be the same.

input2

$(N,\ast ,H_{in2})$ where $H_{in2}=\text{in2\_features}$

weight

$(\text{out\_features},\text{in1\_features},\text{in2\_features})$

bias

$(\text{out\_features})$