+ jRt^RIHtHt^RIHt^RIHtHt^RI H t ^RI H t H t .ROt!RR4t]!R] R 7tRR R lltRR R lltR#)z;Weight Normalization from https://arxiv.org/abs/1602.07868.)AnyTypeVar) deprecated) _weight_normnorm_except_dimModule) ParameterUninitializedParameter WeightNormca]tRt^toV3RlRltV3RlRlt]]!R]R7V3RlRl44t V3R lR lt V3R lR lt V3R lt Rt VtR#)r c*<V^8dQhRS[RS[RR/#)namedimreturnNstrint)format __classdict__s"[/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torch/nn/utils/weight_norm.py __annotate__WeightNorm.__annotate__s"Sstc*VfRpWnW nR#)N)rr)selfrrs&&&r__init__WeightNorm.__init__s ;C rc&<V^8dQhRS[RS[/#)rmodulerrr)rrs"rrrs,,V,,rc\WPR,4p\WPR,4p\W2VP4#)_g_v)getattrrrr)rr!gvs&& 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*<V^8dQhRS[RS[RR/#)rrrrr r)rrs"rrr%s"Cclrc hVPP4F:p\V\4'gKVPV8XgK.\ RV 24h VfRp\W4p\ W4p\V\4'd \R4hVPVVPVR,\\V^V4P44VPVR,\VP44\WVPV44VP!V4V#)z?rc2<V^8dQh/S[;R&S[;R&#)rrrr)rrs"rrrs I Hr)rrN)__name__ __module__ __qualname____firstlineno__rr) staticmethodr FutureWarningr;r@rE__annotate_func____static_attributes____classdictcell__)rs@rr r sb,,  E   B;;@@}rT_module)boundcHV^8dQhR\R\R\R\/#)rr!rrr)rQrr)rs"rrrTs(>>>>S>>rc2\PWV4V#)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:: >>> warnings.filterwarnings("ignore", message=".*torch.nn.utils.weight_norm") # docs: hide >>> 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 r;)r!rrs&&&r weight_normrUTszV3' Mrc<V^8dQhR\R\R\/#)rr!rr)rQr)rs"rrrs&GGxGsG(GrcVPP4FPwr#\V\4'gKVPV8XgK0VP V4VPVVu# \ RV RV 24h)alRemove the weight normalization reparameterization from a module. Args: module (Module): containing module name (str, optional): name of weight parameter Example: >>> warnings.filterwarnings( ... "ignore", message=".*torch.nn.utils.weight_norm" ... ) # docs: hide >>> m = weight_norm(nn.Linear(20, 40)) >>> remove_weight_norm(m) zweight_norm of 'z' not found in )r.itemsr0r rr@r2)r!rkr8s&& rremove_weight_normrZsq,,224 dJ ' 'DII,= KK ))!,M 5 'v_VHE FFrN)r rUrZ)r:)r:)__doc__typingrrtyping_extensionsrtorchrrtorch.nn.modulesrtorch.nn.parameterr r __all__r rQrUrZrrrdsKB(/#@ >?@?@D :V ,>BGGr