Copy current averaged parameters into given collection of parameters. Args: parameters: Iterable of `torch.nn.Parameter`; the parameters to be updated with the stored moving averages. If `None`, the parameters with which this `Exponential
(self, parameters: Iterable[torch.nn.Parameter])
| 760 | s_param.copy_(param) |
| 761 | |
| 762 | def copy_to(self, parameters: Iterable[torch.nn.Parameter]) -> None: |
| 763 | """ |
| 764 | Copy current averaged parameters into given collection of parameters. |
| 765 | |
| 766 | Args: |
| 767 | parameters: Iterable of `torch.nn.Parameter`; the parameters to be |
| 768 | updated with the stored moving averages. If `None`, the parameters with which this |
| 769 | `ExponentialMovingAverage` was initialized will be used. |
| 770 | """ |
| 771 | parameters = list(parameters) |
| 772 | if self.foreach: |
| 773 | torch._foreach_copy_( |
| 774 | [param.data for param in parameters], |
| 775 | [s_param.to(param.device).data for s_param, param in zip(self.shadow_params, parameters)], |
| 776 | ) |
| 777 | else: |
| 778 | for s_param, param in zip(self.shadow_params, parameters): |
| 779 | param.data.copy_(s_param.to(param.device).data) |
| 780 | |
| 781 | def pin_memory(self) -> None: |
| 782 | r""" |