o H h*@sddlZddlZddlmZddlmZddlmZddlmZm Z ddl m Z dgZ dd Z d d Zd d ZGdddeZdS)N)Tensor) constraints) Distribution)_standard_normal lazy_property)_sizeMultivariateNormalcCst||ddS)a Performs a batched matrix-vector product, with compatible but different batch shapes. This function takes as input `bmat`, containing :math:`n \times n` matrices, and `bvec`, containing length :math:`n` vectors. Both `bmat` and `bvec` may have any number of leading dimensions, which correspond to a batch shape. They are not necessarily assumed to have the same batch shape, just ones which can be broadcasted. )torchmatmul unsqueezesqueeze)bmatbvecr[/var/www/vscode/kcb/lib/python3.10/site-packages/torch/distributions/multivariate_normal.py _batch_mvs rcCs|d}|jdd}t|}|d}||}||}|d|}|jd|} t|jdd|j|dD] \} } | | | | f7} q:| |f7} || }tt|tt||dtt|d|d|g} || }|d||} |d| d|}|ddd}t j j | |dd d d}|}||jdd}tt|}t|D] }|||||g7}q||}||S) aK Computes the squared Mahalanobis distance :math:`\mathbf{x}^\top\mathbf{M}^{-1}\mathbf{x}` for a factored :math:`\mathbf{M} = \mathbf{L}\mathbf{L}^\top`. Accepts batches for both bL and bx. They are not necessarily assumed to have the same batch shape, but `bL` one should be able to broadcasted to `bx` one. r NrFupper)sizeshapelendimzipreshapelistrangepermuter linalgsolve_triangularpowsumt)bLbxnbx_batch_shape bx_batch_dims bL_batch_dimsouter_batch_dimsold_batch_dimsnew_batch_dims bx_new_shapesLsx permute_dimsflat_Lflat_x flat_x_swapM_swapM permuted_Mpermute_inv_dimsi reshaped_Mrrr_batch_mahalanobissB   &        r<cCsZtjt|d}tt|ddd}tj|jd|j|jd}tjj ||dd}|S)N)rr rr dtypedeviceFr) r r!choleskyflip transposeeyerr>r?r")PLfL_invIdLrrr_precision_to_scale_trilOs rIcseZdZdZejejejejdZejZ dZ    dfdd Z dfdd Z e d efd d Ze d efd d Ze d efddZed efddZed efddZed efddZefded efddZddZddZZS)ra Creates a multivariate normal (also called Gaussian) distribution parameterized by a mean vector and a covariance matrix. The multivariate normal distribution can be parameterized either in terms of a positive definite covariance matrix :math:`\mathbf{\Sigma}` or a positive definite precision matrix :math:`\mathbf{\Sigma}^{-1}` or a lower-triangular matrix :math:`\mathbf{L}` with positive-valued diagonal entries, such that :math:`\mathbf{\Sigma} = \mathbf{L}\mathbf{L}^\top`. This triangular matrix can be obtained via e.g. Cholesky decomposition of the covariance. Example: >>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_LAPACK) >>> # xdoctest: +IGNORE_WANT("non-deterministic") >>> m = MultivariateNormal(torch.zeros(2), torch.eye(2)) >>> m.sample() # normally distributed with mean=`[0,0]` and covariance_matrix=`I` tensor([-0.2102, -0.5429]) Args: loc (Tensor): mean of the distribution covariance_matrix (Tensor): positive-definite covariance matrix precision_matrix (Tensor): positive-definite precision matrix scale_tril (Tensor): lower-triangular factor of covariance, with positive-valued diagonal Note: Only one of :attr:`covariance_matrix` or :attr:`precision_matrix` or :attr:`scale_tril` can be specified. Using :attr:`scale_tril` will be more efficient: all computations internally are based on :attr:`scale_tril`. If :attr:`covariance_matrix` or :attr:`precision_matrix` is passed instead, it is only used to compute the corresponding lower triangular matrices using a Cholesky decomposition. )loccovariance_matrixprecision_matrix scale_trilTNcs|dkr td|du|du|dudkrtd|durC|dkr*tdt|jdd|jdd}||d|_nI|durj|dkrQtd t|jdd|jdd}||d|_n"|dkrttd t|jdd|jdd}||d|_||d |_ |j jdd}t j |||d |dur||_ dS|durtj ||_ dSt||_ dS) Nrz%loc must be at least one-dimensional.zTExactly one of covariance_matrix or precision_matrix or scale_tril may be specified.rzZscale_tril matrix must be at least two-dimensional, with optional leading batch dimensionsrr )r r zZcovariance_matrix must be at least two-dimensional, with optional leading batch dimensionszYprecision_matrix must be at least two-dimensional, with optional leading batch dimensions)r  validate_args)r ValueErrorr broadcast_shapesrexpandrMrKrLrJsuper__init___unbroadcasted_scale_trilr!r@rI)selfrJrKrLrMrO batch_shape event_shape __class__rrrTsT      zMultivariateNormal.__init__cs|t|}t|}||j}||j|j}|j||_|j|_d|jvr/|j ||_ d|jvr;|j ||_ d|jvrG|j ||_ t t|j ||jdd|j|_|S)NrKrMrLFrN)_get_checked_instancerr SizerXrJrRrU__dict__rKrMrLrSrT_validate_args)rVrW _instancenew loc_shape cov_shaperYrrrRs"       zMultivariateNormal.expandreturncCs|j|j|j|jSN)rUrR _batch_shape _event_shaperVrrrrMszMultivariateNormal.scale_trilcCs&t|j|jj|j|j|jSrd)r r rUmTrRrerfrgrrrrKs  z$MultivariateNormal.covariance_matrixcCs t|j|j|j|jSrd)r cholesky_inverserUrRrerfrgrrrrLs z#MultivariateNormal.precision_matrixcC|jSrdrJrgrrrmeanzMultivariateNormal.meancCrjrdrkrgrrrmodermzMultivariateNormal.modecCs |jdd|j|jS)Nrr )rUr#r$rRrerfrgrrrvariances zMultivariateNormal.variance sample_shapecCs2||}t||jj|jjd}|jt|j|S)Nr=)_extended_shaperrJr>r?rrU)rVrprepsrrrrsamples zMultivariateNormal.rsamplecCsf|jr||||j}t|j|}|jjdddd}d|jdt dt j ||S)Nrr dim1dim2grr) r^_validate_samplerJr<rUdiagonallogr$rfmathpi)rVvaluediffr7 half_log_detrrrlog_probs   &zMultivariateNormal.log_probcCs^|jjdddd}d|jddtdtj|}t|jdkr)|S| |jS)Nrr rtg?rg?r) rUrxryr$rfrzr{rrerR)rVr~Hrrrentropys & zMultivariateNormal.entropy)NNNNrd)__name__ __module__ __qualname____doc__r real_vectorpositive_definitelower_choleskyarg_constraintssupport has_rsamplerTrRrrrMrKrLpropertyrlrnror r\rrsrr __classcell__rrrYrrXs<%9 )rzr rtorch.distributionsr torch.distributions.distributionrtorch.distributions.utilsrr torch.typesr__all__rr<rIrrrrrs    2