!Ei SrSSKJrJr SSKJr SSKJrJr SSK J r SSK J r J r /SQr"SS 5r\"S \ S 9rSS \S \S\S\4SjjrSS \S \S\4Sjjrg)z;Weight Normalization from https://arxiv.org/abs/1602.07868.)AnyTypeVar) deprecated) _weight_normnorm_except_dim)Module) ParameterUninitializedParameter) WeightNorm weight_normremove_weight_normc\rSrSr%\\S'\\S'S\S\SS4SjrS\S\ 4Sjr \ \ "S \ S 9S\S\SS4S j55rS\SS4S jrS\S \ SS4SjrSrg)r namedimreturnNc&UcSnXlX lg)N)rr)selfrrs W/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torch/nn/utils/weight_norm.py__init__WeightNorm.__init__s ;C modulec[XRS-5n[XRS-5n[X2UR5$N_g_v)getattrrrr)rrgvs rcompute_weightWeightNorm.compute_weights9 FII, - FII, -A$((++rze`torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.)categoryc PURR5H8n[U[5(dMURU:XdM,[ SU35e UcSn[X5n[ X5n[U[5(a [S5eURU URUS-[[USU5R55 URUS-[UR55 [XURU55 UR!U5 U$)Nz?r)rr)__name__ __module__ __qualname____firstlineno__str__annotations__intrrrr" staticmethodr FutureWarningr4r8r<__static_attributes__rrr r s I HSst,V,,  E Ccl  B;V;;@v@s@t@rr T_module)boundrrrrc2[RXU5 U$)aApply weight normalization to a parameter in the given module. .. math:: \mathbf{w} = g \dfrac{\mathbf{v}}{\|\mathbf{v}\|} Weight normalization is a reparameterization that decouples the magnitude of a weight tensor from its direction. This replaces the parameter specified by :attr:`name` (e.g. ``'weight'``) with two parameters: one specifying the magnitude (e.g. ``'weight_g'``) and one specifying the direction (e.g. ``'weight_v'``). Weight normalization is implemented via a hook that recomputes the weight tensor from the magnitude and direction before every :meth:`~Module.forward` call. By default, with ``dim=0``, the norm is computed independently per output channel/plane. To compute a norm over the entire weight tensor, use ``dim=None``. See https://arxiv.org/abs/1602.07868 .. warning:: This function is deprecated. Use :func:`torch.nn.utils.parametrizations.weight_norm` which uses the modern parametrization API. The new ``weight_norm`` is compatible with ``state_dict`` generated from old ``weight_norm``. Migration guide: * The magnitude (``weight_g``) and direction (``weight_v``) are now expressed as ``parametrizations.weight.original0`` and ``parametrizations.weight.original1`` respectively. If this is bothering you, please comment on https://github.com/pytorch/pytorch/issues/102999 * To remove the weight normalization reparameterization, use :func:`torch.nn.utils.parametrize.remove_parametrizations`. * The weight is no longer recomputed once at module forward; instead, it will be recomputed on every access. To restore the old behavior, use :func:`torch.nn.utils.parametrize.cached` before invoking the module in question. Args: module (Module): containing module name (str, optional): name of weight parameter dim (int, optional): dimension over which to compute the norm Returns: The original module with the weight norm hook Example:: >>> m = weight_norm(nn.Linear(20, 40), name='weight') >>> m Linear(in_features=20, out_features=40, bias=True) >>> m.weight_g.size() torch.Size([40, 1]) >>> m.weight_v.size() torch.Size([40, 20]) )r r4)rrrs rr r TsxV3' MrcURR5HNup#[U[5(dMURU:XdM.UR U5 URU Us $ [ SUSU35e)zRemove the weight normalization reparameterization from a module. Args: module (Module): containing module name (str, optional): name of weight parameter Example: >>> m = weight_norm(nn.Linear(20, 40)) >>> remove_weight_norm(m) zweight_norm of 'z' not found in )r'itemsr)r rr8r+)rrkr1s rr r sq,,224 dJ ' 'DII,= KK ))!,M 5 'v_VHE FFrN)r3r)r3)__doc__typingrrtyping_extensionsrtorchrrtorch.nn.modulesrtorch.nn.parameterr r __all__r rIrBrDr r rHrrrVsyB(/#@ >?@?@D :V ,===S==@GxGsG(Gr