torch.nn.functional.linear#

torch.nn.functional.linear(input,weight,bias=None)→Tensor#

Applies a linear transformation to the incoming data:$y=x{A}^T+b$y=xAT+b.

This operation supports 2-Dweight withsparse layout

Warning

Sparse support is a beta feature and some layout(s)/dtype/device combinations may not be supported,or may not have autograd support. If you notice missing functionality pleaseopen a feature request.

This operator supportsTensorFloat32.

Shape:

• Input:$(\ast ,in\mathrm{\_}features)$(∗,in_features) where* means any number ofadditional dimensions, including none

• Weight:$(out\mathrm{\_}features,in\mathrm{\_}features)$(out_features,in_features) or$(in\mathrm{\_}features)$(in_features)

• Bias:$(out\mathrm{\_}features)$(out_features) or$()$()

• Output:$(\ast ,out\mathrm{\_}features)$(∗,out_features) or$(\ast )$(∗), based on the shape of the weight