tensorplay.nn.functional.linear

tensorplay.nn.functional.linear(input: TensorBase, weight: TensorBase, bias: TensorBase | None = None) → TensorBase[source]

Applies a linear transformation to the incoming data: $y = xA^T + b$.

Shape:

• Input: $(*, H_\text{in})$ where $*$ means any number of dimensions including none and $H_\text{in} = \text{in\_features}$.

• Weight: $(H_\text{out}, H_\text{in})$ where $H_\text{out} = \text{out\_features}$.

• Bias: $(H_\text{out})$

• Output: $(*, H_\text{out})$

See Linear for more details.