!EiOSSKrSSKJs Jr SSKJr SSKJrJ r /SQr "SS\ 5r "SS \ 5r "S S \\ 5r "S S \ 5r"SS\\ 5r"SS\ 5r"SS\\ 5rg)N)Tensor) _LazyNormBase _NormBase)InstanceNorm1dInstanceNorm2dInstanceNorm3dLazyInstanceNorm1dLazyInstanceNorm2dLazyInstanceNorm3dc ^\rSrSrSS\S\S\S\S\SS4 U4S jjjrS rS r S r S r SU4Sjjr S\ S\ 4SjrSrU=r$) _InstanceNormN num_featuresepsmomentumaffinetrack_running_statsreturnc4>XgS.n[T U]"XX4U40UD6 g)N)devicedtype)super__init__) selfrrrrrrrfactory_kwargs __class__s Z/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torch/nn/modules/instancenorm.pyr_InstanceNorm.__init__s*%+;  x1D HV c[eNNotImplementedErrorrinputs r_check_input_dim_InstanceNorm._check_input_dim%!!r c[er"r#rs r_get_no_batch_dim_InstanceNorm._get_no_batch_dim(r)r c`URURS55RS5$)Nr)_apply_instance_norm unsqueezesqueezer%s r_handle_no_batch_input$_InstanceNorm._handle_no_batch_input+s'(();<DDQGGr c 4[R"UURURURUR UR =(d UR(+URbURUR5$SUR5$)Ng) F instance_norm running_mean running_varweightbiastrainingrrrr%s rr/"_InstanceNorm._apply_instance_norm.sy        KK II MM 9!9!99!]]6DMM HH  =@ HH  r c >URSS5nUcUR(d/n SHn X*-n X;dMU RU 5 M! [U 5S:acURSR SR SU 55UR RS95 U Hn URU 5 M [T U])UUUUUUU5 g)Nversion)r7r8raUnexpected running stats buffer(s) {names} for {klass} with track_running_stats=False. If state_dict is a checkpoint saved before 0.4.0, this may be expected because {klass} does not track running stats by default since 0.4.0. Please remove these keys from state_dict. If the running stats are actually needed, instead set track_running_stats=True in {klass} to enable them. See the documentation of {klass} for details.z and c3.# UH nSUS3v M g7f)"N).0ks r 6_InstanceNorm._load_from_state_dict..Ws*P=OQqc8=Os)namesklass) getrappendlenformatjoinr__name__popr_load_from_state_dict) r state_dictprefixlocal_metadatastrict missing_keysunexpected_keys error_msgsr>running_stats_keysnamekeyrs rrO#_InstanceNorm._load_from_state_dict:s!$$Y5 ?4#;#;!# 7m$&--c28%&*!!@AG%ll*P=O*PP"nn55AGA .CNN3'. %        r r&c URU5 UR5UR5- nURU5UR:waXUR (a.[ SUSURSURU5S35e[R"SUS3SS9 UR5UR5:XaURU5$URU5$) Nzexpected input's size at dim=z to match num_features (z ), but got: .zinput's size at dim=z does not match num_features. You can silence this warning by not passing in num_features, which is not used because affine=False) stacklevel) r'dimr,sizerr ValueErrorwarningswarnr2r/)rr& feature_dims rforward_InstanceNorm.forwardhs e$iikD$:$:$<< ::k "d&7&7 7{{ 3K=A**+< ;8O7PPQS  *;-8== !  99;$002 2..u5 5((//r rA)gh㈵>g?FFNNrN)rM __module__ __qualname____firstlineno__intfloatboolrr'r,r2r/rOrre__static_attributes__ __classcell__)rs@rrrs$)          "      ""H  ,  , \0V000r rc0\rSrSrSrS\4SjrSSjrSrg) ra Applies Instance Normalization. This operation applies Instance Normalization over a 2D (unbatched) or 3D (batched) input as described in the paper `Instance Normalization: The Missing Ingredient for Fast Stylization `__. .. math:: y = \frac{x - \mathrm{E}[x]}{ \sqrt{\mathrm{Var}[x] + \epsilon}} * \gamma + \beta The mean and standard-deviation are calculated per-dimension separately for each object in a mini-batch. :math:`\gamma` and :math:`\beta` are learnable parameter vectors of size `C` (where `C` is the number of features or channels of the input) if :attr:`affine` is ``True``. The variance is calculated via the biased estimator, equivalent to `torch.var(input, correction=0)`. By default, this layer uses instance statistics computed from input data in both training and evaluation modes. If :attr:`track_running_stats` is set to ``True``, during training this layer keeps running estimates of its computed mean and variance, which are then used for normalization during evaluation. The running estimates are kept with a default :attr:`momentum` of 0.1. .. note:: This :attr:`momentum` argument is different from one used in optimizer classes and the conventional notion of momentum. Mathematically, the update rule for running statistics here is :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momentum} \times x_t`, where :math:`\hat{x}` is the estimated statistic and :math:`x_t` is the new observed value. .. note:: :class:`InstanceNorm1d` and :class:`LayerNorm` are very similar, but have some subtle differences. :class:`InstanceNorm1d` is applied on each channel of channeled data like multidimensional time series, but :class:`LayerNorm` is usually applied on entire sample and often in NLP tasks. Additionally, :class:`LayerNorm` applies elementwise affine transform, while :class:`InstanceNorm1d` usually don't apply affine transform. Args: num_features: number of features or channels :math:`C` of the input eps: a value added to the denominator for numerical stability. Default: 1e-5 momentum: the value used for the running_mean and running_var computation. Default: 0.1 affine: a boolean value that when set to ``True``, this module has learnable affine parameters, initialized the same way as done for batch normalization. Default: ``False``. track_running_stats: a boolean value that when set to ``True``, this module tracks the running mean and variance, and when set to ``False``, this module does not track such statistics and always uses batch statistics in both training and eval modes. Default: ``False`` Shape: - Input: :math:`(N, C, L)` or :math:`(C, L)` - Output: :math:`(N, C, L)` or :math:`(C, L)` (same shape as input) Examples:: >>> # Without Learnable Parameters >>> m = nn.InstanceNorm1d(100) >>> # With Learnable Parameters >>> m = nn.InstanceNorm1d(100, affine=True) >>> input = torch.randn(20, 100, 40) >>> output = m(input) rcgNr]rAr+s rr, InstanceNorm1d._get_no_batch_dimr NcfUR5S;a[SUR5S35egN)r]zexpected 2D or 3D input (got D input)r_rar%s rr'InstanceNorm1d._check_input_dim0 99;f $`__. .. math:: y = \frac{x - \mathrm{E}[x]}{ \sqrt{\mathrm{Var}[x] + \epsilon}} * \gamma + \beta The mean and standard-deviation are calculated per-dimension separately for each object in a mini-batch. :math:`\gamma` and :math:`\beta` are learnable parameter vectors of size `C` (where `C` is the input size) if :attr:`affine` is ``True``. The standard-deviation is calculated via the biased estimator, equivalent to `torch.var(input, correction=0)`. By default, this layer uses instance statistics computed from input data in both training and evaluation modes. If :attr:`track_running_stats` is set to ``True``, during training this layer keeps running estimates of its computed mean and variance, which are then used for normalization during evaluation. The running estimates are kept with a default :attr:`momentum` of 0.1. .. note:: This :attr:`momentum` argument is different from one used in optimizer classes and the conventional notion of momentum. Mathematically, the update rule for running statistics here is :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momentum} \times x_t`, where :math:`\hat{x}` is the estimated statistic and :math:`x_t` is the new observed value. .. note:: :class:`InstanceNorm2d` and :class:`LayerNorm` are very similar, but have some subtle differences. :class:`InstanceNorm2d` is applied on each channel of channeled data like RGB images, but :class:`LayerNorm` is usually applied on entire sample and often in NLP tasks. Additionally, :class:`LayerNorm` applies elementwise affine transform, while :class:`InstanceNorm2d` usually don't apply affine transform. Args: num_features: :math:`C` from an expected input of size :math:`(N, C, H, W)` or :math:`(C, H, W)` eps: a value added to the denominator for numerical stability. Default: 1e-5 momentum: the value used for the running_mean and running_var computation. Default: 0.1 affine: a boolean value that when set to ``True``, this module has learnable affine parameters, initialized the same way as done for batch normalization. Default: ``False``. track_running_stats: a boolean value that when set to ``True``, this module tracks the running mean and variance, and when set to ``False``, this module does not track such statistics and always uses batch statistics in both training and eval modes. Default: ``False`` Shape: - Input: :math:`(N, C, H, W)` or :math:`(C, H, W)` - Output: :math:`(N, C, H, W)` or :math:`(C, H, W)` (same shape as input) Examples:: >>> # Without Learnable Parameters >>> m = nn.InstanceNorm2d(100) >>> # With Learnable Parameters >>> m = nn.InstanceNorm2d(100, affine=True) >>> input = torch.randn(20, 100, 35, 45) >>> output = m(input) rcgNrxrAr+s rr, InstanceNorm2d._get_no_batch_dim9rur NcfUR5S;a[SUR5S35egN)rxzexpected 3D or 4D input (got ryrzr%s rr'InstanceNorm2d._check_input_dim<r|r rArgr}rAr rrrsDL3Tr rc4\rSrSrSr\rS\4SjrSSjr Sr g) r iAaFA :class:`torch.nn.InstanceNorm2d` module with lazy initialization of the ``num_features`` argument. The ``num_features`` argument of the :class:`InstanceNorm2d` is inferred from the ``input.size(1)``. The attributes that will be lazily initialized are `weight`, `bias`, `running_mean` and `running_var`. Check the :class:`torch.nn.modules.lazy.LazyModuleMixin` for further documentation on lazy modules and their limitations. Args: num_features: :math:`C` from an expected input of size :math:`(N, C, H, W)` or :math:`(C, H, W)` eps: a value added to the denominator for numerical stability. Default: 1e-5 momentum: the value used for the running_mean and running_var computation. Default: 0.1 affine: a boolean value that when set to ``True``, this module has learnable affine parameters, initialized the same way as done for batch normalization. Default: ``False``. track_running_stats: a boolean value that when set to ``True``, this module tracks the running mean and variance, and when set to ``False``, this module does not track such statistics and always uses batch statistics in both training and eval modes. Default: ``False`` Shape: - Input: :math:`(N, C, H, W)` or :math:`(C, H, W)` - Output: :math:`(N, C, H, W)` or :math:`(C, H, W)` (same shape as input) rcgrrAr+s rr,$LazyInstanceNorm2d._get_no_batch_dim_rur NcfUR5S;a[SUR5S35egrrzr%s rr'#LazyInstanceNorm2d._check_input_dimbr|r rArg) rMrhrirjr~rrrkr,r'rnrAr rr r A 6#M3Tr r c0\rSrSrSrS\4SjrSSjrSrg) r igab Applies Instance Normalization. This operation applies Instance Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension) as described in the paper `Instance Normalization: The Missing Ingredient for Fast Stylization `__. .. math:: y = \frac{x - \mathrm{E}[x]}{ \sqrt{\mathrm{Var}[x] + \epsilon}} * \gamma + \beta The mean and standard-deviation are calculated per-dimension separately for each object in a mini-batch. :math:`\gamma` and :math:`\beta` are learnable parameter vectors of size C (where C is the input size) if :attr:`affine` is ``True``. The standard-deviation is calculated via the biased estimator, equivalent to `torch.var(input, correction=0)`. By default, this layer uses instance statistics computed from input data in both training and evaluation modes. If :attr:`track_running_stats` is set to ``True``, during training this layer keeps running estimates of its computed mean and variance, which are then used for normalization during evaluation. The running estimates are kept with a default :attr:`momentum` of 0.1. .. note:: This :attr:`momentum` argument is different from one used in optimizer classes and the conventional notion of momentum. Mathematically, the update rule for running statistics here is :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momentum} \times x_t`, where :math:`\hat{x}` is the estimated statistic and :math:`x_t` is the new observed value. .. note:: :class:`InstanceNorm3d` and :class:`LayerNorm` are very similar, but have some subtle differences. :class:`InstanceNorm3d` is applied on each channel of channeled data like 3D models with RGB color, but :class:`LayerNorm` is usually applied on entire sample and often in NLP tasks. Additionally, :class:`LayerNorm` applies elementwise affine transform, while :class:`InstanceNorm3d` usually don't apply affine transform. Args: num_features: :math:`C` from an expected input of size :math:`(N, C, D, H, W)` or :math:`(C, D, H, W)` eps: a value added to the denominator for numerical stability. Default: 1e-5 momentum: the value used for the running_mean and running_var computation. Default: 0.1 affine: a boolean value that when set to ``True``, this module has learnable affine parameters, initialized the same way as done for batch normalization. Default: ``False``. track_running_stats: a boolean value that when set to ``True``, this module tracks the running mean and variance, and when set to ``False``, this module does not track such statistics and always uses batch statistics in both training and eval modes. Default: ``False`` Shape: - Input: :math:`(N, C, D, H, W)` or :math:`(C, D, H, W)` - Output: :math:`(N, C, D, H, W)` or :math:`(C, D, H, W)` (same shape as input) Examples:: >>> # Without Learnable Parameters >>> m = nn.InstanceNorm3d(100) >>> # With Learnable Parameters >>> m = nn.InstanceNorm3d(100, affine=True) >>> input = torch.randn(20, 100, 35, 45, 10) >>> output = m(input) rcgNrrAr+s rr, InstanceNorm3d._get_no_batch_dimrur NcfUR5S;a[SUR5S35egN)rzexpected 4D or 5D input (got ryrzr%s rr'InstanceNorm3d._check_input_dimr|r rArgr}rAr rr r gsCJ3Tr r c4\rSrSrSr\rS\4SjrSSjr Sr g) r iaXA :class:`torch.nn.InstanceNorm3d` module with lazy initialization of the ``num_features`` argument. The ``num_features`` argument of the :class:`InstanceNorm3d` is inferred from the ``input.size(1)``. The attributes that will be lazily initialized are `weight`, `bias`, `running_mean` and `running_var`. Check the :class:`torch.nn.modules.lazy.LazyModuleMixin` for further documentation on lazy modules and their limitations. Args: num_features: :math:`C` from an expected input of size :math:`(N, C, D, H, W)` or :math:`(C, D, H, W)` eps: a value added to the denominator for numerical stability. Default: 1e-5 momentum: the value used for the running_mean and running_var computation. Default: 0.1 affine: a boolean value that when set to ``True``, this module has learnable affine parameters, initialized the same way as done for batch normalization. Default: ``False``. track_running_stats: a boolean value that when set to ``True``, this module tracks the running mean and variance, and when set to ``False``, this module does not track such statistics and always uses batch statistics in both training and eval modes. Default: ``False`` Shape: - Input: :math:`(N, C, D, H, W)` or :math:`(C, D, H, W)` - Output: :math:`(N, C, D, H, W)` or :math:`(C, D, H, W)` (same shape as input) rcgrrAr+s rr,$LazyInstanceNorm3d._get_no_batch_dimrur NcfUR5S;a[SUR5S35egrrzr%s rr'#LazyInstanceNorm3d._check_input_dimr|r rArg) rMrhrirjr~r rrkr,r'rnrAr rr r rr r )rbtorch.nn.functionalnn functionalr5torchr batchnormrr__all__rrr rr r r rAr rrs/ h0Ih0VJT]JTZ"T "TJLT]LT^#T #TLKT]KT\#T #Tr