torch.nn.functional.bilinear

torch.nn.functional.bilinear(input1, input2, weight, bias=None)

Applies a bilinear transformation to the incoming data: $y = x_1^T A x_2 + b$

Shape:

• input1: $(N, *, H_{in1})$ where $H_{in1}=\text{in1\_features}$ and $*$ means any number of additional dimensions. All but the last dimension of the inputs should be the same.

• input2: $(N, *, H_{in2})$ where $H_{in2}=\text{in2\_features}$

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

• bias: $(\text{out\_features})$

• output: $(N, *, H_{out})$ where $H_{out}=\text{out\_features}$ and all but the last dimension are the same shape as the input.