.apply()

Run the op, build the graph node, and wire up the backward step.

Parameters:

• *inputs (object, default: () ) –

  Tensor and non-Tensor arguments forwarded to forward and output_shape. Non-Tensor inputs are ignored during gradient accumulation.

• oper (str | None, default: None ) –

  Optional label override for the graph node. Falls back to cls.oper then cls.__name__.

Returns:

• 'Tensor' –

  Output tensor wired into the computation graph.