3jJ? SrSSKrSSKJr SSKrSSKJs Jr SSK J r SSK J r SSK J r S S\RS \\\4S \S \\R\R44S jjrS \RS\\\4S \R4SjrS\RS\S \R4SjrS!S\RS\S\S\S \R4 SjjrS\RS\RS \R4SjrS\RS\RS \R4Sjr\ S"S\RS\S \\\4S\S \R4 Sjj5rg)#zHIn this module several equalization methods are exposed: he, ahe, clahe.N)Tuple_torch_histc_cast)perform_keep_shape_image) histogramimgs grid_sizeeven_tile_sizereturncUnURSSupE[R"XAS- 5n[R"XQS- 5nU(a XfS-(aSOS- nXwS-(aSOS- nXaS-U- nXqS-U- n XRS:dXRS:a [S5eUS:dU S:a[R "USU SU/SS 9nURS n UR SX5R SXf5R S Xw5RS5R5n U RS US:wa[eU RS US:wa[eX4$)a\Compute tiles on an image according to a grid size. Note that padding can be added to the image in order to crop properly the image. So, the grid_size (GH, GW) x tile_size (TH, TW) >= image_size (H, W) Args: imgs: batch of 2D images with shape (B, C, H, W) or (C, H, W). grid_size: number of tiles to be cropped in each direction (GH, GW) even_tile_size: Determine if the width and height of the tiles must be even. Returns: tensor with tiles (B, GH, GW, C, TH, TW). B = 1 in case of a single image is provided. tensor with the padded batch of 2D imageswith shape (B, C, H', W'). NrrzBCannot compute tiles on the image according to the given grid sizereflect)mode) shapemathceil ValueErrorFpadunfoldsqueeze contiguousAssertionError) r r r batchhw kernel_vert kernel_horzpad_vertpad_horzctiless U/home/wildlama/miniconda3/lib/python3.13/site-packages/kornia/enhance/equalization.py_compute_tilesr+ sg$E ;;rs DAyyq\!12Kyyq\!12K!Oq2 !Oq2 q\)A-Hq\)A-H++b/!X B%?]^^!|x!|ea1h7iH[[_A Q ; , ; , jl   {{2)A,& {{2)A,& < padded_imgs tile_sizec^UR5S:wa [S5eURSUS-S:wa [S5eURSUS-S:wa [S5eUSS-nUSS-nURS nURSXD5RSX"5RS X35R S5R 5nURS U:wa[eURSUSS- :wa[eURSUSS- :wa[eU$) aCompute interpolation tiles on a properly padded set of images. Note that images must be padded. So, the tile_size (TH, TW) * grid_size (GH, GW) = image_size (H, W) Args: padded_imgs: batch of 2D images with shape (B, C, H, W) already padded to extract tiles of size (TH, TW). tile_size: shape of the current tiles (TH, TW). Returns: tensor with the interpolation tiles (B, 2GH, 2GW, C, TH/2, TW/2). zImages Tensor must be 4D.rrz Images are not correctly padded.rrrrr)dimr rrrr)r-r.interp_kernel_vertinterp_kernel_horzr( interp_tiless r*_compute_interpolation_tilesr5ZsCA899y|+q0?@@y|+q0?@@(la/'la/   r "A1a# % : % : jl """1!11"1!11 r,r)binsc[XSSS9$)Nrrr6minmaxr)r)r6s r* _my_histcr;s U1! <r?bghgwr(thtwpixelsr)tilehistosr6max_valclippedresidualredistv_range mat_range lut_scalelutss r* _compute_lutsrgs"~~1122%++A2"'F$//"f5E  99 ! ! # #[[ch!ich[_"3DQTU"Vch!ijF[[c)UJU?? xxzQ677!- 2 2H"A[[AUZZ 0F Av,,q"q&)..rAvq9==aw=W|^<aA NO [[AUZZ 0F Av,,q"q&)..rAvq9==aw=W|^<aA NO ). r1aB0"L?? xxzQ677 ), =K#/"4"4H"+7*<)B)B)D)L)LRQS)T/99"=DDXSUWXZ[bd]de [!%9: L  r1aR 0%*$4$4\$BO  QVaZR|/A/A,J]J]^ S2X\ 4 ! 2r  B   1b  $ $Q /B QVaZR|/A/A,J]J]^ S2X\  AF  1b  $ $Q /B ))R!VM1b - 5 5b1fa H R RST UC ))R!VM1a + 5 5a 8C/q!B$"}=DDQGNBB b#uyyR01A b#uyyR01A%*]]1c599Q?%KOAqtQrTM"4MQPQP[UWZ[U[P[]^]hbdghbh]hjkMk3lOAq{BF{AKaK/0+1adA:6==a@JAq!Q"'--3;;q>599QPQ?"SOAqtQJ*1adBF?;BB1EJAq!Q',}}Q A RSUV'XOAqtR!VO$2!Q"*=DDQGD%A"'--sEIIdE[U[5(d[S[U535e[U[5(d[S[U535e[ U5S:wa[S[ U535e[US[5(d[US[5(a [S5eUSS::d USS::a[ SU35eUn[XBS 5upVURS URS 4n[Xg5n[XQUS 9n [X5n U RSS SSSS5RU5n URS SupU SSU 2SU 24n UR5U R5:waU RS5n U $)a5Apply clahe equalization on the input tensor. .. image:: _static/img/equalize_clahe.png NOTE: Lut computation uses the same approach as in OpenCV, in next versions this can change. Args: input: images tensor to equalize with values in the range [0, 1] and shape :math:`(*, C, H, W)`. clip_limit: threshold value for contrast limiting. If 0 clipping is disabled. grid_size: number of tiles to be cropped in each direction (GH, GW). slow_and_differentiable: flag to select implementation Returns: Equalized image or images with shape as the input. Examples: >>> img = torch.rand(1, 10, 20) >>> res = equalize_clahe(img) >>> res.shape torch.Size([1, 10, 20]) >>> img = torch.rand(2, 3, 10, 20) >>> res = equalize_clahe(img) >>> res.shape torch.Size([2, 3, 10, 20]) z(Input clip_limit type is not float. Got z'Input grid_size type is not Tuple. Got rz4Input grid_size is not a Tuple with 2 elements. Got rrz=Input grid_size type is not valid, must be a Tuple[int, int].z/Input grid_size elements must be positive. Got Trr)r>r?rr0rjN.) isinstancefloat TypeErrortypetuplerJrr+rr5rgrrs reshape_asr1r)rrr rr hist_tiles img_paddedr.r4rfequalized_tileseq_imgsr"r#s r*equalize_claherKsD j% ( (B4 CSBTUVV i ' 'A$y/ARSTT 9~NsS\~N^_``)A,&&*Yq\5*I*IWXX|qIaLA-J9+VWWD ,DTBJ","2"22"6 8H8H8L!MI!=j!TL&*AD%=\$PO,33Aq!Q1EPPQ[\G ::bc?DAc2A2rrk"G yy{gkkm#//!$ Nr,)F)D@F)r)rF)__doc__rtypingrrDtorch.nn.functionalnn functionalrkornia.core.utilsrkornia.image.utilsrrTensorintboolr+r5r;rrgr{rrr,r*rs$O  /7 LQ7 ,,7#(c?7DH7 5<< %&7t,ell,uSRUX,[`[g[g,^=U\\=== UZ3 3(+39>3MQ3 \\3l5ELL5 55pM&5<<M&u||M&PUP\P\M&`!'$) G <<GGS#XG" G  \\ GGr,