affine¶

dragon.vm.torch.nn.functional.affine(
  input,
  weight,
  bias=None,
  dim=- 1,
  out=None
)[source]¶

Apply affine transformation to input.

\[\text{out} = \text{input} \times \text{weight} + \text{bias} \]

Parameters:

• input (dragon.vm.torch.Tensor) – The input tensor.
• weight (dragon.vm.torch.Tensor) – The weight tensor.
• bias (dragon.vm.torch.Tensor, optional) – The bias tensor.
• dim (Union[int, Sequence[int]], optional) – The dimension to apply.
• out (dragon.vm.torch.Tensor, optional) – The output tensor.

Returns:

dragon.vm.torch.Tensor – The output tensor.

See also

torch.nn.Affine(…)