o wZh_O@sddlZddlmmZddlmZddlmZm Z gdZ Gddde Z Gdd d e Z Gd d d ee Z Gd d d e ZGdddee ZGddde ZGdddee ZdS)N)Tensor) _LazyNormBase _NormBase)InstanceNorm1dInstanceNorm2dInstanceNorm3dLazyInstanceNorm1dLazyInstanceNorm2dLazyInstanceNorm3dc seZdZ      ddedededed ed df fd d Zd dZddZddZ ddZ fddZ de d e fddZ ZS) _InstanceNormh㈵>皙?FN num_featuresepsmomentumaffinetrack_running_statsreturnc s*||d}tj|||||fi|dS)N)devicedtype)super__init__) selfrrrrrrrZfactory_kwargs __class__L/var/www/auris/lib/python3.10/site-packages/torch/nn/modules/instancenorm.pyrs   z_InstanceNorm.__init__cCtNNotImplementedErrorrinputrrr_check_input_dim%z_InstanceNorm._check_input_dimcCrrr rrrr_get_no_batch_dim(r%z_InstanceNorm._get_no_batch_dimcCs||ddS)Nr)_apply_instance_normZ unsqueezeZsqueezer"rrr_handle_no_batch_input+sz$_InstanceNorm._handle_no_batch_inputc CsBt||j|j|j|j|jp|j |jdur|j|j Sd|j S)Ng) FZ instance_norm running_mean running_varweightZbiasZtrainingrrrr"rrrr(.s z"_InstanceNorm._apply_instance_normc s|dd}|durE|jsEg} dD]} || } | |vr | | qt| dkrE|djddd| D|jjd| D]} || q=t |||||||dS) Nversion)r+r,raUnexpected running stats buffer(s) {names} for {klass} with track_running_stats=False. If state_dict is a checkpoint saved before 0.4.0, this may be expected because {klass} does not track running stats by default since 0.4.0. Please remove these keys from state_dict. If the running stats are actually needed, instead set track_running_stats=True in {klass} to enable them. See the documentation of {klass} for details.z and css|] }d|dVqdS)"Nr).0krrr Wsz6_InstanceNorm._load_from_state_dict..)namesklass) getrappendlenformatjoinr__name__popr_load_from_state_dict) rZ state_dictprefixZlocal_metadatastrictZ missing_keysZunexpected_keys error_msgsr.Zrunning_stats_keysnamekeyrrrr<:s6    z#_InstanceNorm._load_from_state_dictr#c Cs||||}|||jkr3|jr*td|d|jd||dtd|d||kr@| |S| |S)Nzexpected input's size at dim=z to match num_features (z ), but got: .zinput's size at dim=z does not match num_features. You can silence this warning by not passing in num_features, which is not used because affine=False) r$dimr'sizerr ValueErrorwarningswarnr)r()rr#Z feature_dimrrrforwardhs"    z_InstanceNorm.forward)r rFFNN)r: __module__ __qualname__intfloatboolrr$r'r)r(r<rrH __classcell__rrrrr s4  .r c@ eZdZdZddZddZdS)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, unbiased=False)`. 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) cCdSNrr&rrrr'r%z InstanceNorm1d._get_no_batch_dimcC$|dvrtd|ddSN)rRzexpected 2D or 3D input (got D input)rCrEr"rrrr$ zInstanceNorm1d._check_input_dimNr:rIrJ__doc__r'r$rrrrrsD rc@$eZdZdZeZddZddZdS)r aA :class:`torch.nn.InstanceNorm1d` module with lazy initialization of the ``num_features`` argument. The ``num_features`` argument of the :class:`InstanceNorm1d` 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, L)` or :math:`(C, L)` 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) cCrPrQrr&rrrr'r%z$LazyInstanceNorm1d._get_no_batch_dimcCrSrTrWr"rrrr$rXz#LazyInstanceNorm1d._check_input_dimN)r:rIrJrZr cls_to_becomer'r$rrrrr s  r c@rO)ra$ Applies Instance Normalization. This operation applies Instance Normalization over a 4D input (a mini-batch of 2D 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, unbiased=False)`. 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) cCrPNrUrr&rrrr'8r%z InstanceNorm2d._get_no_batch_dimcCrSN)rUzexpected 3D or 4D input (got rVrWr"rrrr$;rXzInstanceNorm2d._check_input_dimNrYrrrrrsF rc@r[)r aA :class:`torch.nn.InstanceNorm2d` module with lazy initialization of the ``num_features`` argument. The ``num_features`` argument of the :class:`InstanceNorm2d` is inferred from the ``input.size(1)``. The attributes that will be lazily initialized are `weight`, `bias`, `running_mean` and `running_var`. Check the :class:`torch.nn.modules.lazy.LazyModuleMixin` for further documentation on lazy modules and their limitations. Args: num_features: :math:`C` from an expected input of size :math:`(N, C, H, W)` or :math:`(C, H, W)` eps: a value added to the denominator for numerical stability. Default: 1e-5 momentum: the value used for the running_mean and running_var computation. Default: 0.1 affine: a boolean value that when set to ``True``, this module has learnable affine parameters, initialized the same way as done for batch normalization. Default: ``False``. track_running_stats: a boolean value that when set to ``True``, this module tracks the running mean and variance, and when set to ``False``, this module does not track such statistics and always uses batch statistics in both training and eval modes. Default: ``False`` Shape: - Input: :math:`(N, C, H, W)` or :math:`(C, H, W)` - Output: :math:`(N, C, H, W)` or :math:`(C, H, W)` (same shape as input) cCrPr]rr&rrrr'^r%z$LazyInstanceNorm2d._get_no_batch_dimcCrSr^rWr"rrrr$arXz#LazyInstanceNorm2d._check_input_dimN)r:rIrJrZrr\r'r$rrrrr @  r c@rO)ra@ 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, unbiased=False)`. 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) cCrPNr_rr&rrrr'r%z InstanceNorm3d._get_no_batch_dimcCrSN)r_zexpected 4D or 5D input (got rVrWr"rrrr$rXzInstanceNorm3d._check_input_dimNrYrrrrrfsE rc@r[)r aA :class:`torch.nn.InstanceNorm3d` module with lazy initialization of the ``num_features`` argument. The ``num_features`` argument of the :class:`InstanceNorm3d` is inferred from the ``input.size(1)``. The attributes that will be lazily initialized are `weight`, `bias`, `running_mean` and `running_var`. Check the :class:`torch.nn.modules.lazy.LazyModuleMixin` for further documentation on lazy modules and their limitations. Args: num_features: :math:`C` from an expected input of size :math:`(N, C, D, H, W)` or :math:`(C, D, H, W)` eps: a value added to the denominator for numerical stability. Default: 1e-5 momentum: the value used for the running_mean and running_var computation. Default: 0.1 affine: a boolean value that when set to ``True``, this module has learnable affine parameters, initialized the same way as done for batch normalization. Default: ``False``. track_running_stats: a boolean value that when set to ``True``, this module tracks the running mean and variance, and when set to ``False``, this module does not track such statistics and always uses batch statistics in both training and eval modes. Default: ``False`` Shape: - Input: :math:`(N, C, D, H, W)` or :math:`(C, D, H, W)` - Output: :math:`(N, C, D, H, W)` or :math:`(C, D, H, W)` (same shape as input) cCrPrarr&rrrr'r%z$LazyInstanceNorm3d._get_no_batch_dimcCrSrbrWr"rrrr$rXz#LazyInstanceNorm3d._check_input_dimN)r:rIrJrZrr\r'r$rrrrr r`r )rFZtorch.nn.functionalnnZ functionalr*ZtorchrZ batchnormrr__all__r rr rr rr rrrrs  jM%O&N