pytorch / 2 / generated / torch.nn.bilinear.html

Bilinear

class torch.nn.Bilinear(in1_features, in2_features, out_features, bias=True, device=None, dtype=None) [source]

Applies a bilinear transformation to the incoming data: y = x 1 T A x 2 + b y = x_1^T A x_2 + b

Parameters
  • in1_features (int) – size of each first input sample
  • in2_features (int) – size of each second input sample
  • out_features (int) – size of each output sample
  • bias (bool) – If set to False, the layer will not learn an additive bias. Default: True
Shape:
  • Input1: ( , H i n 1 ) (*, H_{in1}) where H i n 1 = in1_features H_{in1}=\text{in1\_features} and * means any number of additional dimensions including none. All but the last dimension of the inputs should be the same.
  • Input2: ( , H i n 2 ) (*, H_{in2}) where H i n 2 = in2_features H_{in2}=\text{in2\_features} .
  • Output: ( , H o u t ) (*, H_{out}) where H o u t = out_features H_{out}=\text{out\_features} and all but the last dimension are the same shape as the input.
Variables
  • weight (torch.Tensor) – the learnable weights of the module of shape ( out_features , in1_features , in2_features ) (\text{out\_features}, \text{in1\_features}, \text{in2\_features}) . The values are initialized from U ( k , k ) \mathcal{U}(-\sqrt{k}, \sqrt{k}) , where k = 1 in1_features k = \frac{1}{\text{in1\_features}}
  • bias – the learnable bias of the module of shape ( out_features ) (\text{out\_features}) . If bias is True, the values are initialized from U ( k , k ) \mathcal{U}(-\sqrt{k}, \sqrt{k}) , where k = 1 in1_features k = \frac{1}{\text{in1\_features}}

Examples:

>>> m = nn.Bilinear(20, 30, 40)
>>> input1 = torch.randn(128, 20)
>>> input2 = torch.randn(128, 30)
>>> output = m(input1, input2)
>>> print(output.size())
torch.Size([128, 40])

© 2024, PyTorch Contributors
PyTorch has a BSD-style license, as found in the LICENSE file.
https://pytorch.org/docs/2.1/generated/torch.nn.Bilinear.html