[^(h dZddlmZmZddlmZddlmZmZddl m Z ddl m Z m Z gdZGdd Zed e Zdd ed ededefdZdd ed edefdZy)z;Weight Normalization from https://arxiv.org/abs/1602.07868.)AnyTypeVar) deprecated) _weight_normnorm_except_dim)Module) ParameterUninitializedParameter) WeightNorm weight_normremove_weight_normceZdZUeed<eed<dededdfdZdedefdZ e e de dededdfd Z deddfd Zded eddfd Zy)r namedimreturnNc(|d}||_||_y)N)rr)selfrrs X/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/torch/nn/utils/weight_norm.py__init__zWeightNorm.__init__s ;C modulect||jdz}t||jdz}t|||jSN_g_v)getattrrrr)rrgvs rcompute_weightzWeightNorm.compute_weights? FDII, - FDII, -Aq$((++rze`torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.)categoryc 8|jjD]0}t|ts|j|k(s$t d||d}t||}t ||}t|tr td|j|=|j|dztt|d|j|j|dzt|jt|||j||j!||S)Nz?r)__name__ __module__ __qualname__str__annotations__intrrrr staticmethodr FutureWarningr1r4r7rrr r s I HSst,V,,  E Ccl  B;V;;@v@s@t@rr T_module)boundrrrrc4tj||||S)aE Apply 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 reparametrization, 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 r1)rrrs rr r SsxVT3' Mrc|jjD]G\}}t|ts|j|k(s'|j ||j|=|cSt d|d|)aRemove 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 rr4r()rrkr.s rr r su,,2244 dJ 'DII,= KK ))!,M  'v_VHE FFrN)r0r)r0)__doc__typingrrtyping_extensionsrtorchrrtorch.nn.modulesrtorch.nn.parameterr r __all__r rAr;r=r r r@rrrNsyB(/#@ >?@?@D :V ,===S==@GxGsG(Gr