- torch.nn.functional.linear(input, weight, bias=None) Tensor ¶
Applies a linear transformation to the incoming data: .
This opperation supports 2-D
weightwith sparse layout
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 please open a feature request.
This operator supports TensorFloat32.
Input: where * means any number of additional dimensions, including none
Output: or , based on the shape of the weight