3j(SSKJrJr SSKrSS\RS\RS\RS\S\\R\R44 SjjrSS \RS \RS\S\R4S jjrSS \RS\RS \RS\S\R4 SjjrSS\RS\RS\RS \RS\S\R4 Sjjr SS\RS\S\S\ S \\S\\RS\ S\ S\S\\R\R44Sjjr g))OptionalTupleNvaluesbinssigmaepsilonreturncl[U[R5(d[S[ U535e[U[R5(d[S[ U535e[U[R5(d[S[ U535eUR 5S:Xd[ SUR35eUR 5S:Xd[ SUR35eUR 5S:Xd[ S UR35eXRS5RS5- n[R"S XB- RS 5-5n[R"USS 9n[R"USS 9RS5U-nXg- nXe4$) aCalculate the marginal probability distribution function of the input based on the number of histogram bins. Args: values: shape [BxNx1]. bins: shape [NUM_BINS]. sigma: shape [1], gaussian smoothing factor. epsilon: scalar, for numerical stability. Returns: Tuple[torch.Tensor, torch.Tensor]: - torch.Tensor: shape [BxN]. - torch.Tensor: shape [BxNxNUM_BINS]. z-Input values type is not a torch.Tensor. Got z+Input bins type is not a torch.Tensor. Got z,Input sigma type is not a torch.Tensor. Got z/Input values must be a of the shape BxNx1. Got z0Input bins must be a of the shape NUM_BINS. Got rz*Input sigma must be a of the shape 1. Got dim) isinstancetorchTensor TypeErrortyper ValueErrorshape unsqueezeexppowmeansum)rrrr residuals kernel_valuespdf normalizations R/home/wildlama/miniconda3/lib/python3.13/site-packages/kornia/enhance/histogram.py marginal_pdfr"sh" fell + +GV ~VWW dELL ) )Ed4j\RSS eU\\ * *FtE{mTUU ::<1 J6<<.YZZ 88:?KDJJ<XYY 99;! Eekk]STT*44Q77IIIdi&7%<%CCB1MPWWM  -C Jr#x bandwidthcB[URS5XU5upEU$)aEstimate the histogram of the input torch.Tensor. The calculation uses kernel density estimation which requires a bandwidth (smoothing) parameter. Args: x: Input torch.Tensor to compute the histogram with shape :math:`(B, D)`. bins: The number of bins to use the histogram :math:`(N_{bins})`. bandwidth: Gaussian smoothing factor with shape shape [1]. epsilon: A scalar, for numerical stability. Returns: Computed histogram of shape :math:`(B, N_{bins})`. Examples: >>> x = torch.rand(1, 10) >>> bins = torch.torch.linspace(0, 255, 128) >>> hist = histogram(x, bins, bandwidth=torch.tensor(0.9)) >>> hist.shape torch.Size([1, 128]) r)r"r)r-rr.rr_s r! histogramr1is!,!++a.$7 CFC Jr#x1x2c[URS5X#U5upV[URS5X#U5upW[Xg5nU$)aAEstimate the 2d histogram of the input torch.Tensor. The calculation uses kernel density estimation which requires a bandwidth (smoothing) parameter. Args: x1: Input torch.Tensor to compute the histogram with shape :math:`(B, D1)`. x2: Input torch.Tensor to compute the histogram with shape :math:`(B, D2)`. bins: The number of bins to use the histogram :math:`(N_{bins})`. bandwidth: Gaussian smoothing factor with shape shape [1]. epsilon: A scalar, for numerical stability. Default: 1e-10. Returns: Computed histogram of shape :math:`(B, N_{bins}), N_{bins})`. Examples: >>> x1 = torch.rand(2, 32) >>> x2 = torch.rand(2, 32) >>> bins = torch.torch.linspace(0, 255, 128) >>> hist = histogram2d(x1, x2, bins, bandwidth=torch.tensor(0.9)) >>> hist.shape torch.Size([2, 128, 128]) r)r"rr,) r2r3rr.rr0r$r%rs r! histogram2dr5sE4%R\\!_dwOA$R\\!_dwOA N 3C Jr#imageminmaxn_binscenters return_pdfkernelepsc lUb7[U[R5(d[S[ U5S35eUb7[U[R5(d[S[ U5S35eUbF[ UR 5S:a-UR5S:wa[SUR S35e[U[5(d[S[ U5S35e[U[5(d[S[ U5S35e[U[5(d[S [ U5S35eUb-[U[5(d[S [ U5S35e[U[5(d[S [ U5S35eUcX!- U- nUc1X[R"X0RURS 9S ---nURSSSSS5n[R "UR#S5U- 5U- n US:Xa[R$"SU S--5n OWUS;aBU S:*R'U R5n US:Xa SU - U -n O$US:XaU n OSU S-- U -n O[SUS35e[R("U SS9R+SSS5n U(a[R("U SSS9U-n X- nUR5S:Xa#U R-5n UR-5nX4$UR5S:Xa"U R-S5n UR-S5nX4$UR5S:XaU R-5n O%UR5S:XaU R-S5n U [R."U 54$)a*Estimate the histogram of the input image(s). The calculation uses triangular kernel density estimation. Args: image: Input torch.Tensor to compute the histogram with shape :math:`(H, W)`, :math:`(C, H, W)` or :math:`(B, C, H, W)`. min: Lower end of the interval (inclusive). max: Upper end of the interval (inclusive). Ignored when :attr:`centers` is specified. n_bins: The number of histogram bins. Ignored when :attr:`centers` is specified. bandwidth: Smoothing factor. If not specified or equal to -1, :math:`(bandwidth = (max - min) / n_bins)`. centers: Centers of the bins with shape :math:`(n_bins,)`. If not specified or empty, it is calculated as centers of equal width bins of [min, max] range. return_pdf: If True, also return probability densities for each bin. kernel: kernel to perform kernel density estimation ``(`triangular`, `gaussian`, `uniform`, `epanechnikov`)``. eps: epsilon for numerical stability. Returns: Computed histogram of shape :math:`(bins)`, :math:`(C, bins)`, :math:`(B, C, bins)`. Computed probability densities of shape :math:`(bins)`, :math:`(C, bins)`, :math:`(B, C, bins)`, if return_pdf is ``True``. torch.Tensor of torch.zeros with shape of the histogram otherwise. z,Input image type is not a torch.Tensor. Got .z.Bins' centers type is not a torch.Tensor. Got rr zABins' centers must be a torch.Tensor of the shape (n_bins,). Got z3Type of lower end of the range is not a float. Got z3Type of upper end of the range is not a float. Got z*Type of number of bins is not an int. Got z#Bandwidth type is not a float. Got z#Return_pdf type is not a bool. Got )devicedtypeg?r'gaussianr r) triangularuniform epanechnikovrCg?rDzJKernel must be 'triangular', 'gaussian', 'uniform' or 'epanechnikov'. Got )r'rT)rkeepdimr )rrrrrlenrrrfloatintboolaranger@rAreshapeabsrrtorpermutesqueeze zeros_like)r6r7r8r9r.r:r;r<r=urmaskhistr rs r!image_histogram2drVs]T E5<N=OqQRRY&( U\\&UZU`U`%adg%ghhoob!Q1-G %//!$w./);A  $A+. < <Q{{177# \ ! 1W,M y  M 1a4Z4/Meflemmnopp 99] 1 9 9!Q BD $B=C " 99;! <<>D++-CyYY[A <<?D++a.Cy yy{a||~  ||A !!$' ''r#)绽|=)ggo@NNFrCrW)typingrrrrrIr"r,r1r5rJrKstrrVr#r!r\s$# UZ* LL* % *5:\\*LQ* 5<< %&*Z"ell"ELL"SX"ejeqeq"JU\\ellUZglgsgs8gl ,,.3llGL||^c \\H!%&*k( <<k( k( k(  k(  k( ell # k(k( k( k( 5<< %&k(r#