2VhTTddlmZddlmZddlmZddlmZddlmZddlm Z ddl m Z Gdd e Z ed d=d Z Gd de Zedd=dZGdde Zedd=dZGdde Zed d>dZ d>dZGdde Zed d?dZGdde Zed  d@d!Z d@d"ZGd#d$e Zed% dAd&ZGd'd(e Zed) dBd*Z d=d+ZGd,d-e Zed. dBd/Z d=d0Z!Gd1d2e Z"ed3 dCd4Z#Gd5d6e Z$ed7 dDd8Z%Gd9d:e Z&ed; dEd<Z'y )F)backend)ops) keras_export) KerasTensor)any_symbolic_tensors) Operation)compute_conv_output_shapec,eZdZdfd ZdZdZxZS)RGBToGrayscalecVt|tj||_yNsuper__init__rstandardize_data_format data_formatselfr __class__s C/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/ops/image.pyrzRGBToGrayscale.__init__ ! "::;GcXtjj||jSNr)rimagergb_to_grayscalerrimagess rcallzRGBToGrayscale.calls)}}--  0 0.  rct|j}t|dvrtd||jdk(rd|d<nd|d<t ||j S)NhInvalid images rank: expected rank 3 (single image) or rank 4 (batch of images). Received: images.shape= channels_lastshapedtype)listr+len ValueErrorrrr,)rr images_shapes rcompute_output_specz"RGBToGrayscale.compute_output_specsnFLL) | F ***69     . L  L V\\BBrr __name__ __module__ __qualname__rr r1 __classcell__rs@rr r sH Crr z keras.ops.image.rgb_to_grayscaleNct|frt|j|Stjj ||S)aConvert RGB images to grayscale. This function converts RGB images to grayscale images. It supports both 3D and 4D tensors. Args: images: Input image or batch of images. Must be 3D or 4D. data_format: A string specifying the data format of the input tensor. It can be either `"channels_last"` or `"channels_first"`. `"channels_last"` corresponds to inputs with shape `(batch, height, width, channels)`, while `"channels_first"` corresponds to inputs with shape `(batch, channels, height, width)`. If not specified, the value will default to `keras.config.image_data_format`. Returns: Grayscale image or batch of grayscale images. Examples: >>> import numpy as np >>> from keras import ops >>> x = np.random.random((2, 4, 4, 3)) >>> y = ops.image.rgb_to_grayscale(x) >>> y.shape (2, 4, 4, 1) >>> x = np.random.random((4, 4, 3)) # Single RGB image >>> y = ops.image.rgb_to_grayscale(x) >>> y.shape (4, 4, 1) >>> x = np.random.random((2, 3, 4, 4)) >>> y = ops.image.rgb_to_grayscale(x, data_format="channels_first") >>> y.shape (2, 1, 4, 4) r)rr symbolic_callrrrrrs rrr#s?NVI&+6DDVLL == ) )&k ) JJrc,eZdZdfd ZdZdZxZS)RGBToHSVcVt|tj||_yr rrs rrzRGBToHSV.__init__PrrcXtjj||jSr)rr rgb_to_hsvrrs rr z RGBToHSV.callT"}}''D>> import numpy as np >>> from keras import ops >>> x = np.random.random((2, 4, 4, 3)) >>> y = ops.image.rgb_to_hsv(x) >>> y.shape (2, 4, 4, 3) >>> x = np.random.random((4, 4, 3)) # Single RGB image >>> y = ops.image.rgb_to_hsv(x) >>> y.shape (4, 4, 3) >>> x = np.random.random((2, 3, 4, 4)) >>> y = ops.image.rgb_to_hsv(x, data_format="channels_first") >>> y.shape (2, 3, 4, 4) r)rr<r9rrr?r:s rr?r?hs?TVI&K0>>vFF == # #F # DDrc,eZdZdfd ZdZdZxZS)HSVToRGBcVt|tj||_yr rrs rrzHSVToRGB.__init__rrcXtjj||jSr)rr hsv_to_rgbrrs rr z HSVToRGB.callr@rct|j}|j}t|dvrt d|t j |st d|t||jSrBrCrEs rr1zHSVToRGB.compute_output_specrFrr r2r7s@rrJrJrGrrJzkeras.ops.image.hsv_to_rgbct|frt|j|Stjj ||S)aConvert HSV images to RGB. `images` must be of float dtype, and the output is only well defined if the values in `images` are in `[0, 1]`. Args: images: Input image or batch of images. Must be 3D or 4D. data_format: A string specifying the data format of the input tensor. It can be either `"channels_last"` or `"channels_first"`. `"channels_last"` corresponds to inputs with shape `(batch, height, width, channels)`, while `"channels_first"` corresponds to inputs with shape `(batch, channels, height, width)`. If not specified, the value will default to `keras.config.image_data_format`. Returns: RGB image or batch of RGB images. Examples: >>> import numpy as np >>> from keras import ops >>> x = np.random.random((2, 4, 4, 3)) >>> y = ops.image.hsv_to_rgb(x) >>> y.shape (2, 4, 4, 3) >>> x = np.random.random((4, 4, 3)) # Single HSV image >>> y = ops.image.hsv_to_rgb(x) >>> y.shape (4, 4, 3) >>> x = np.random.random((2, 3, 4, 4)) >>> y = ops.image.hsv_to_rgb(x, data_format="channels_first") >>> y.shape (2, 3, 4, 4) r)rrJr9rrrMr:s rrMrMs?NVI&K0>>vFF == # #F # DDrc:eZdZ dfd ZdZdZxZS)Resizec t |t||_||_||_||_||_||_||_ tj||_ yr ) rrtuplesize interpolation antialiascrop_to_aspect_ratiopad_to_aspect_ratio fill_mode fill_valuerrr) rrTrUrVrWrXrYrZrrs rrzResize.__init__s[ $K *"$8!#6 "$"::;Grc t||j|j|j|j|j |j |j|j S)NrUrVrrWrXrYrZ) _resizerTrUrVrrWrXrYrZrs rr z Resize.callsR  II,,nn((!%!:!: $ 8 8nn  rc t|j}t|dvrtd|j|jdk(rd\}}nd\}}|j d||<|j d||<t ||jS) Nr"yInvalid images rank: expected rank 3 (single image) or rank 4 (batch of images). Received input with shape: images.shape=r&r)rar(rr'r*)r-r+r.r/rrTrr,)rrr0 height_axis width_axiss rr1zResize.compute_output_specsFLL) | F * & ~/     .&, #K&, #K$(IIaL [!#'99Q< Z V\\BBrbilinearFFFconstantNr2r7s@rrQrQs+!"!H*  CrrQzkeras.ops.image.resizec lt|dk7rtd|t|jdkst|jdkDrtd|j|r |r tdt|fr"t ||||||||j |St ||||||||| S) a Resize images to size using the specified interpolation method. Args: images: Input image or batch of images. Must be 3D or 4D. size: Size of output image in `(height, width)` format. interpolation: Interpolation method. Available methods are `"nearest"`, `"bilinear"`, and `"bicubic"`. Defaults to `"bilinear"`. antialias: Whether to use an antialiasing filter when downsampling an image. Defaults to `False`. crop_to_aspect_ratio: If `True`, resize the images without aspect ratio distortion. When the original aspect ratio differs from the target aspect ratio, the output image will be cropped so as to return the largest possible window in the image (of size `(height, width)`) that matches the target aspect ratio. By default (`crop_to_aspect_ratio=False`), aspect ratio may not be preserved. pad_to_aspect_ratio: If `True`, pad the images without aspect ratio distortion. When the original aspect ratio differs from the target aspect ratio, the output image will be evenly padded on the short side. fill_mode: When using `pad_to_aspect_ratio=True`, padded areas are filled according to the given mode. Only `"constant"` is supported at this time (fill with constant value, equal to `fill_value`). fill_value: Float. Padding value to use when `pad_to_aspect_ratio=True`. data_format: A string specifying the data format of the input tensor. It can be either `"channels_last"` or `"channels_first"`. `"channels_last"` corresponds to inputs with shape `(batch, height, width, channels)`, while `"channels_first"` corresponds to inputs with shape `(batch, channels, height, width)`. If not specified, the value will default to `keras.config.image_data_format`. Returns: Resized image or batch of images. Examples: >>> x = np.random.random((2, 4, 4, 3)) # batch of 2 RGB images >>> y = keras.ops.image.resize(x, (2, 2)) >>> y.shape (2, 2, 2, 3) >>> x = np.random.random((4, 4, 3)) # single RGB image >>> y = keras.ops.image.resize(x, (2, 2)) >>> y.shape (2, 2, 3) >>> x = np.random.random((2, 3, 4, 4)) # batch of 2 RGB images >>> y = keras.ops.image.resize(x, (2, 2), ... data_format="channels_first") >>> y.shape (2, 3, 2, 2) z +  3   VI& '#!5 3!   -    #1/  rc 0tjj||||||||| } | j|jk(r| Stj|jrt j | } t j| |jS)Nrk)rrrlr, is_int_dtyperround saturate_cast) rrTrUrVrWrXrYrZrresizeds rr]r]zsmm"" #1/# G}} $FLL)))G$   Wfll 33rc4eZdZ dfd ZdZdZxZS)AffineTransformct|||_||_||_t j ||_yr )rrrUrYrZrrr)rrUrYrZrrs rrzAffineTransform.__init__s9 *"$"::;Grctjj|||j|j|j |j S)NrUrYrZr)rraffine_transformrUrYrZrrr transforms rr zAffineTransform.callsD}}--  ,,nn(( .  rct|jdvrtd|jt|jdvrtd|jt|j|jS)Nr"r_)r'rjzInvalid transform rank: expected rank 1 (single transform) or rank 2 (batch of transforms). Received input with shape: transform.shape=r,r.r+r/rr,rxs rr1z#AffineTransform.compute_output_specs~ v|| F * & ~/  y v -##,??"35  6<>> x = np.random.random((2, 64, 80, 3)) # batch of 2 RGB images >>> transform = np.array( ... [ ... [1.5, 0, -20, 0, 1.5, -16, 0, 0], # zoom ... [1, 0, -20, 0, 1, -16, 0, 0], # translation ... ] ... ) >>> y = keras.ops.image.affine_transform(x, transform) >>> y.shape (2, 64, 80, 3) >>> x = np.random.random((64, 80, 3)) # single RGB image >>> transform = np.array([1.0, 0.5, -20, 0.5, 1.0, -16, 0, 0]) # shear >>> y = keras.ops.image.affine_transform(x, transform) >>> y.shape (64, 80, 3) >>> x = np.random.random((2, 3, 64, 80)) # batch of 2 RGB images >>> transform = np.array( ... [ ... [1.5, 0, -20, 0, 1.5, -16, 0, 0], # zoom ... [1, 0, -20, 0, 1, -16, 0, 0], # translation ... ] ... ) >>> y = keras.ops.image.affine_transform(x, transform, ... data_format="channels_first") >>> y.shape (2, 3, 64, 80) rv)rrsr9rrrw)rryrUrYrZrs rrwrwsifVY/0'!#  - *  + == ) )# * rc4eZdZ dfd ZdZdZxZS)ExtractPatchesct|t|tr||f}||_||_||_||_tj||_ yr ) rr isinstanceintrTstrides dilation_ratepaddingrrr)rrTrrrrrs rrzExtractPatches.__init__&sS  dC $ 1` is not supported in conjunction with `dilation_rate > 1` padding: The type of padding algorithm to use: `"same"` or `"valid"`. data_format: A string specifying the data format of the input tensor. It can be either `"channels_last"` or `"channels_first"`. `"channels_last"` corresponds to inputs with shape `(batch, height, width, channels)`, while `"channels_first"` corresponds to inputs with shape `(batch, channels, height, width)`. If not specified, the value will default to `keras.config.image_data_format`. Returns: Extracted patches 3D (if not batched) or 4D (if batched) Examples: >>> image = np.random.random( ... (2, 20, 20, 3) ... ).astype("float32") # batch of 2 RGB images >>> patches = keras.ops.image.extract_patches(image, (5, 5)) >>> patches.shape (2, 4, 4, 75) >>> image = np.random.random((20, 20, 3)).astype("float32") # 1 RGB image >>> patches = keras.ops.image.extract_patches(image, (3, 3), (1, 1)) >>> patches.shape (18, 18, 27) )rTrrrrr)rrr9rrs rextract_patchesr\sSZVI&'#  -    g}g; rct|tr|x}}n't|dk(r |d|d}}ntd|t j |}|dk(r|j d}n|dk(r|j d}|s|}||zz} tjj| |j } tjj| |||| f} d } t|j d k(r#d } tjj|d }tjj|| ||||} | r!tjj| d } | S)Nrjrr'zPInvalid `size` argument. Expected an int or a tuple of length 2. Received: size=r&r(channels_firstr)r{Fr#T)axis)inputskernelrrrr)rrr. TypeErrorrrr+numpyeyer,reshape expand_dimsnnconvsqueeze) rrTrrrrpatch_hpatch_wrout_dimr _unbatchedpatchess rrrsh$  ' Ta7DG ::> A  11+>Ko%ll2& ( (ll2& +-G ]]  wfll  ;F ]] " "';8FJ 6<<A **6*:jjoo# G--''a'8 Nrc,eZdZdfd ZdZdZxZS)MapCoordinatescLt|||_||_||_yr )rrorderrYrZ)rrrYrZrs rrzMapCoordinates.__init__s#  "$rctjj|||j|j|j S)N)rrYrZ)rrmap_coordinatesrrYrZrr coordinatess rr zMapCoordinates.calls9}},,  **nn -  rcD|jdt|jk7r(td|jd|jdt|jdkrtd|jt|jdd|jS)NrzaFirst dim of `coordinates` must be the same as the rank of `inputs`. Received inputs with shape: z and coordinate leading dim of rjzOInvalid coordinates rank: expected at least rank 2. Received input with shape: r'r{)r+r.r/rr,rs rr1z"MapCoordinates.compute_output_specs   Q 3v||#4 4//5||n=""-"3"3A"6!79  {  !A %//:/@/@.AC ;,,QR0 EErrgrr2r7s@rrrs%   Frrzkeras.ops.image.map_coordinatesct||frt|||j||Stjj |||||S)aMap the input array to new coordinates by interpolation. Note that interpolation near boundaries differs from the scipy function, because we fixed an outstanding bug [scipy/issues/2640](https://github.com/scipy/scipy/issues/2640). Args: inputs: The input array. coordinates: The coordinates at which inputs is evaluated. order: The order of the spline interpolation. The order must be `0` or `1`. `0` indicates the nearest neighbor and `1` indicates the linear interpolation. fill_mode: Points outside the boundaries of the inputs are filled according to the given mode. Available methods are `"constant"`, `"nearest"`, `"wrap"` and `"mirror"` and `"reflect"`. Defaults to `"constant"`. - `"constant"`: `(k k k k | a b c d | k k k k)` The inputs is extended by filling all values beyond the edge with the same constant value k specified by `fill_value`. - `"nearest"`: `(a a a a | a b c d | d d d d)` The inputs is extended by the nearest pixel. - `"wrap"`: `(a b c d | a b c d | a b c d)` The inputs is extended by wrapping around to the opposite edge. - `"mirror"`: `(c d c b | a b c d | c b a b)` The inputs is extended by mirroring about the edge. - `"reflect"`: `(d c b a | a b c d | d c b a)` The inputs is extended by reflecting about the edge of the last pixel. fill_value: Value used for points outside the boundaries of the inputs if `fill_mode="constant"`. Defaults to `0`. Returns: Output input or batch of inputs. )rrr9rrr)rrrrYrZs rrrs^PV[12     - ,  - == ( (   rc:eZdZ dfd ZdZdZxZS) PadImagesct|||_||_||_||_||_||_tj||_ yr ) rr top_padding left_paddingbottom_padding right_padding target_height target_widthrrr) rrrrrrrrrs rrzPadImages.__init__sS &(,**("::;Grc t||j|j|j|j|j |j |jSr ) _pad_imagesrrrrrrrrs rr zPadImages.call0sQ                        rczt|j}|jdk(rd\}}||||}}nd\}}||||}}|j}|||j|z|j z}|j }|||j|z|jz}|||<|||<t||jS)Nr&r`rbr*) r-r+rrrrrrrrr, rrr0rcrdheightwidthrrs rr1zPadImages.compute_output_spec<sFLL)    .&, #K(5|J7OEF&, #K(5|J7OEF**  V%7 ,,v58K8KKM((  E$5,,u4t7I7IIL$1 [!#/ Z V\\BBrNNNNNNNr2r7s@rrrs+H&  Crrzkeras.ops.image.pad_imagesc ~t|fr t|||||||j|St||||||||S)aPad `images` with zeros to the specified `height` and `width`. Args: images: Input image or batch of images. Must be 3D or 4D. top_padding: Number of rows of zeros to add on top. left_padding: Number of columns of zeros to add on the left. bottom_padding: Number of rows of zeros to add at the bottom. right_padding: Number of columns of zeros to add on the right. target_height: Height of output images. target_width: Width of output images. data_format: A string specifying the data format of the input tensor. It can be either `"channels_last"` or `"channels_first"`. `"channels_last"` corresponds to inputs with shape `(batch, height, width, channels)`, while `"channels_first"` corresponds to inputs with shape `(batch, channels, height, width)`. If not specified, the value will default to `keras.config.image_data_format`. Returns: Padded image or batch of images. Example: >>> images = np.random.random((15, 25, 3)) >>> padded_images = keras.ops.image.pad_images( ... images, 2, 3, target_height=20, target_width=30 ... ) >>> padded_images.shape (20, 30, 3) >>> batch_images = np.random.random((2, 15, 25, 3)) >>> padded_batch = keras.ops.image.pad_images( ... batch_images, 2, 3, target_height=20, target_width=30 ... ) >>> padded_batch.shape (2, 20, 30, 3))rrr9r)rrrrrrrrs r pad_imagesrRsd`VI&         -     rc6tj|}tj|}tj|}t |dvrt d||||gjddk7rt d|d|d||||gjddk7rt d|d|d |t |d k(rd nd } |d k(r |d|d} } n |d|d} } |||z | z }|||z | z }|||z | z }|||z | z }|dkrt d||dkrt d||dkrt d||dkrt d|||g||gg} |d k(r | ddggz} nddgg| z} | rddgg| z} tjj|| } | S)Nr"VInvalid shape for argument `images`: it must have rank 3 or 4. Received: images.shape=r'z^Must specify exactly two of top_padding, bottom_padding, target_height. Received: top_padding=z, bottom_padding=, target_height=z^Must specify exactly two of left_padding, right_padding, target_width. Received: left_padding=z, right_padding=, target_width=r#FTr&r)rar(rz0top_padding must be >= 0. Received: top_padding=z2left_padding must be >= 0. Received: left_padding=z4right_padding must be >= 0. Received: right_padding=z6bottom_padding must be >= 0. Received: bottom_padding=) rrconvert_to_tensorrr+r.r/countrpad)rrrrrrrrr0is_batchrr pad_width padded_imagess rrrs11+>K  & &v .F99V$L <&&&2^ 5  ^]399$?1D %%0M2,-.*O  -   m\288>!C &&2^4*O,(>  +  L)Q.uDHo%$R(,r*:$R(,r*:#n4v= &4v=#m3e; $|3e; Q>{m L  a@ O  q ''4o 7   ((6'7 9  ~.}0MNIo%!Q( VHy( VHy( MM%%fi8M rc.eZdZ dfd ZdZdZxZS) CropImagesct|||_||_||_||_||_||_tj||_ yr ) rr top_croppingbottom_cropping left_croppingright_croppingrrrrr) rrrrrrrrrs rrzCropImages.__init__sS (.*,*("::;Grc t||j|j|j|j|j |j |jSr ) _crop_imagesrrrrrrrrs rr zCropImages.callsQ                      rct|j}|jdk(rd\}}nd\}}||||}}|'|jt d|d|j|'|j t d|d|j |j}|||j z |jz }|j }|||jz |jz }|||<|||<t||jS) Nr&r`rbzbWhen the height of the images is unknown, `target_height` must be specified.Received images.shape=z and target_height=z`When the width of the images is unknown, `target_width` must be specified.Received images.shape=z and target_width=r*) r-r+rrr/rrrrrrr,rs rr1zCropImages.compute_output_specs@FLL)    .&, #K&, #K$[1< 3K >d008))57!!%!3!3 46  =T..6))57 $ 1 124 **  "T%6%669M9MMM((   4#5#558K8KKL$1 [!#/ Z V\\BBrr r2r7s@rrrsH&  !Crrzkeras.ops.image.crop_imagesc ~t|fr t|||||||j|St||||||||S)aCrop `images` to a specified `height` and `width`. Args: images: Input image or batch of images. Must be 3D or 4D. top_cropping: Number of columns to crop from the top. left_cropping: Number of columns to crop from the left. bottom_cropping: Number of columns to crop from the bottom. right_cropping: Number of columns to crop from the right. target_height: Height of the output images. target_width: Width of the output images. data_format: A string specifying the data format of the input tensor. It can be either `"channels_last"` or `"channels_first"`. `"channels_last"` corresponds to inputs with shape `(batch, height, width, channels)`, while `"channels_first"` corresponds to inputs with shape `(batch, channels, height, width)`. If not specified, the value will default to `keras.config.image_data_format`. Returns: Cropped image or batch of images. Example: >>> images = np.reshape(np.arange(1, 28, dtype="float32"), [3, 3, 3]) >>> images[:,:,0] # print the first channel of the images array([[ 1., 4., 7.], [10., 13., 16.], [19., 22., 25.]], dtype=float32) >>> cropped_images = keras.image.crop_images(images, 0, 0, 2, 2) >>> cropped_images[:,:,0] # print the first channel of the cropped images array([[ 1., 4.], [10., 13.]], dtype=float32))rrr9r)rrrrrrrrs r crop_imagesr3sdXVI&         -     rcZtj|}tj|}tj|}t |dvrt d||||gjddk7rt d|d|d||||gjddk7rt d|d|d |t |d k(rd nd } |d k(r|d|d} } |d} n|d|d} } |d} || |z |z }|| |z |z }|| |z |z }|| |z |z }|dkrt d||dkrt d||dkrt d||dkrt d|||g} ||g}|d k(r | dgz} || gz}n dg| z} | g|z}| r|d}dg| z} |g|z}tj|| |}|S)Nr"rr'zaMust specify exactly two of top_cropping, bottom_cropping, target_height. Received: top_cropping=z, bottom_cropping=rzaMust specify exactly two of left_cropping, right_cropping, target_width. Received: left_cropping=z, right_cropping=rr#FTr&r)rar(rz2top_cropping must be >= 0. Received: top_cropping=z4target_height must be >= 0. Received: target_height=z4left_cropping must be >= 0. Received: left_cropping=z2target_width must be >= 0. Received: target_width=) rrrrr+r.r/rslice)rrrrrrrrr0rrrchannels start_indicesr+ batch_sizecropped_imagess rrrvs11+>K  & &v .F99V$L <&&&2^ 5  o}5;;DAQF &&2^4./0*O  -   ~|4::4@AE ''4o6,-.(>  +  L)Q.uDHo%$R(,r*:#$R(,r*:# -? 0<?  ,~= ~- = a@ O  q ''4o 7  q ''4o 7  a@ O  "=1M L )Eo%%+  "m+  U"!!_ m+  u$YYv}e>> x = np.random.random((2, 64, 80, 3)) # batch of 2 RGB images >>> start_points = np.array( ... [ ... [[0, 0], [0, 64], [80, 0], [80, 64]], ... [[0, 0], [0, 64], [80, 0], [80, 64]], ... ] ... ) >>> end_points = np.array( ... [ ... [[3, 5], [7, 64], [76, -10], [84, 61]], ... [[8, 10], [10, 61], [65, 3], [88, 43]], ... ] ... ) >>> y = keras.ops.image.perspective_transform(x, start_points, end_points) >>> y.shape (2, 64, 80, 3) >>> x = np.random.random((64, 80, 3)) # single RGB image >>> start_points = np.array([[0, 0], [0, 64], [80, 0], [80, 64]]) >>> end_points = np.array([[3, 5], [7, 64], [76, -10], [84, 61]]) >>> y = keras.ops.image.perspective_transform(x, start_points, end_points) >>> y.shape (64, 80, 3) >>> x = np.random.random((2, 3, 64, 80)) # batch of 2 RGB images >>> start_points = np.array( ... [ ... [[0, 0], [0, 64], [80, 0], [80, 64]], ... [[0, 0], [0, 64], [80, 0], [80, 64]], ... ] ... ) >>> end_points = np.array( ... [ ... [[3, 5], [7, 64], [76, -10], [84, 61]], ... [[8, 10], [10, 61], [65, 3], [88, 43]], ... ] ... ) >>> y = keras.ops.image.perspective_transform( ... x, start_points, end_points, data_format="channels_first" ... ) >>> y.shape (2, 3, 64, 80) r)rrr9rrr)rrrrUrZrs rrrsj^V\:>?#'!#  - j 9  : == . .# / rc2eZdZ dfd ZdZdZxZS) GaussianBlurcrt|||_||_t j ||_yr )rrrsigmarrr)rrrrrs rrzGaussianBlur.__init__cs2 & "::;Grctjj||j|j|j S)Nrrr)rr gaussian_blurrrrrs rr zGaussianBlur.callns:}}** ((**(( +  rct|jdvrtd|jt|j|jSNr"r_r{r|rs rr1z GaussianBlur.compute_output_specvJ v|| F * & ~/  6<>> x = np.random.random((2, 64, 80, 3)) # batch of 2 RGB images >>> y = keras.ops.image.gaussian_blur(x) >>> y.shape (2, 64, 80, 3) >>> x = np.random.random((64, 80, 3)) # single RGB image >>> y = keras.ops.image.gaussian_blur(x) >>> y.shape (64, 80, 3) >>> x = np.random.random((2, 3, 64, 80)) # batch of 2 RGB images >>> y = keras.ops.image.gaussian_blur( ... x, data_format="channels_first") >>> y.shape (2, 3, 64, 80) r)rrr9rrr)rrrrs rrrs[RVI&##  -   == & & ' rc:eZdZ dfd ZdZdZxZS)ElasticTransformct|||_||_||_||_||_||_tj||_ yr ) rralpharrUrYrZseedrrr) rrrrUrYrZrrrs rrzElasticTransform.__init__sN   *"$ "::;Grc tjj||j|j|j |j |j|j|jS)NrrrUrYrZrr) rrelastic_transformrrrUrYrZrrrs rr zElasticTransform.callsV}}.. ****,,nn((/  rct|jdvrtd|jt|j|jSrr|rs rr1z$ElasticTransform.compute_output_specrrg4@g@rfreflectrhNNr2r7s@rrrs*  H&  =rrz!keras.ops.image.elastic_transformc t|fr!t|||||||j|Stjj ||||||||S)a Applies elastic deformation to the image(s). Args: images: Input image or batch of images. Must be 3D or 4D. alpha: Scaling factor that controls the intensity of the deformation. sigma: Standard deviation of the Gaussian filter used for smoothing the displacement fields. interpolation: Interpolation method. Available methods are `"nearest"`, and `"bilinear"`. Defaults to `"bilinear"`. fill_mode: Points outside the boundaries of the input are filled according to the given mode. Available methods are `"constant"`, `"nearest"`, `"wrap"` and `"reflect"`. Defaults to `"constant"`. - `"reflect"`: `(d c b a | a b c d | d c b a)` The input is extended by reflecting about the edge of the last pixel. - `"constant"`: `(k k k k | a b c d | k k k k)` The input is extended by filling all values beyond the edge with the same constant value k specified by `fill_value`. - `"wrap"`: `(a b c d | a b c d | a b c d)` The input is extended by wrapping around to the opposite edge. - `"nearest"`: `(a a a a | a b c d | d d d d)` The input is extended by the nearest pixel. fill_value: Value used for points outside the boundaries of the input if `fill_mode="constant"`. Defaults to `0`. data_format: A string specifying the data format of the input tensor. It can be either `"channels_last"` or `"channels_first"`. `"channels_last"` corresponds to inputs with shape `(batch, height, width, channels)`, while `"channels_first"` corresponds to inputs with shape `(batch, channels, height, width)`. If not specified, the value will default to `keras.config.image_data_format`. Returns: Transformed image or batch of images with elastic deformation. Examples: >>> x = np.random.random((2, 64, 80, 3)) # batch of 2 RGB images >>> y = keras.ops.image.elastic_transform(x) >>> y.shape (2, 64, 80, 3) >>> x = np.random.random((64, 80, 3)) # single RGB image >>> y = keras.ops.image.elastic_transform(x) >>> y.shape (64, 80, 3) >>> x = np.random.random((2, 3, 64, 80)) # batch of 2 RGB images >>> y = keras.ops.image.elastic_transform( ... x, data_format="channels_first") >>> y.shape (2, 3, 64, 80) r)rrr9rrr)rrrrUrYrZrrs rrrssBVI&'!#  -   == * *#  +  rr rer}rrrrrr)( keras.srcrrkeras.src.api_exportrkeras.src.backendrrkeras.src.ops.operationrkeras.src.ops.operation_utilsr r rr<r?rJrMrQrlr]rsrwrrrrrrrrrrrrrrrrrrrr s-)2-CCYC201(K2(KVCyC2*++E,+E\CyC2*+(E,(EV1CY1Ch&'f(fX4>%=i%=P01 `2`F4@Y4@n/0   717z   +\FYF@/0AB313l3C 3Cl*+C,C\SlACACH+,?-?TZz-=9-=`56  [7[|=9=<-.>B3/3l'=y'=T12   S3Sr