sgfdZddlmZmZmZmZmZmZmZddl Z ddl m Z m Z mZddlmZmZmZmZmZddlmZmZmZmZmZmZmZmZmZmZm Z m!Z!ddl"m#Z#m$Z$m%Z%m&Z&e%rddl'Z'e&jPe)Z*d eed eefd Z+ dd e jXd ee-e-fdeee.efd e jXfdZ/ ddee jXdeee.efd ee-fdZ0 dde jXde-de-de-deee.efd ee-e-ff dZ1Gdde Z2y)z&Image processor class for BridgeTower.)AnyDictIterableListOptionalTupleUnionN)BaseImageProcessor BatchFeature get_size_dict) PaddingMode center_croppadresizeto_channel_dimension_format) OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension ImageInputPILImageResamplingget_image_sizeinfer_channel_dimension_format is_batchedis_scaled_imageto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingvaluesreturncJt|Dcgc] }t|c}Scc}w)zO Return the maximum value across all indices of an iterable of values. )zipmax)r#values_is o/var/www/html/venv/lib/python3.12/site-packages/transformers/models/bridgetower/image_processing_bridgetower.pymax_across_indicesr*/s +.v, 7hCM 77 7s image output_sizeinput_data_formatct||\}}tj|tj}d|d|d|f<|S)a Make a pixel mask for the image, where 1 indicates a valid pixel and 0 indicates padding. Args: image (`np.ndarray`): Image to make the pixel mask for. output_size (`Tuple[int, int]`): Output size of the mask.  channel_dim)dtypeN)rnpzerosint64)r+r,r- input_height input_widthmasks r)make_pixel_maskr97sF!/uBS TL+ 88Krxx 0D()D,  $% KimagescJ|t|d}|tjk(r+t|Dcgc]}|jc}\}}}||fS|tj k(r+t|Dcgc]}|jc}\}}}||fSt d|cc}wcc}w)zH Get the maximum height and width across all images in a batch. rz"Invalid channel dimension format: )rrFIRSTr*shapeLAST ValueError)r;r-img_ max_height max_widths r)get_max_height_widthrEJs  :6!9E,222#5F6SSsyy6S#T :y  "" .33 3#5F6SSsyy6S#T Iq  ""=>O=PQRR 7T6Ss B+B  input_imageshorterlonger size_divisorct||\}}||}}|t||z } ||kr|} | |z} n| |z} |} t| | |kDr|t| | z } | | z} | | z} t| dzt| dz} } | |z|z} | |z|z} | | fS)Ng?)rminr'int) rFrGrHrIr-r6r7min_sizemax_sizescale new_height new_widths r)get_resize_output_image_sizerR]s!/{j>f"d!Z xZ!S)%BridgeTowerImageProcessora3 Constructs a BridgeTower image processor. Args: do_resize (`bool`, *optional*, defaults to `True`): Whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by the `do_resize` parameter in the `preprocess` method. size (`Dict[str, int]` *optional*, defaults to `{'shortest_edge': 288}`): Resize the shorter side of the input to `size["shortest_edge"]`. The longer side will be limited to under `int((1333 / 800) * size["shortest_edge"])` while preserving the aspect ratio. Only has an effect if `do_resize` is set to `True`. Can be overridden by the `size` parameter in the `preprocess` method. size_divisor (`int`, *optional*, defaults to 32): The size by which to make sure both the height and width can be divided. Only has an effect if `do_resize` is set to `True`. Can be overridden by the `size_divisor` parameter in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`): Resampling filter to use if resizing the image. Only has an effect if `do_resize` is set to `True`. Can be overridden by the `resample` parameter in the `preprocess` method. do_rescale (`bool`, *optional*, defaults to `True`): Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale` parameter in the `preprocess` method. rescale_factor (`int` or `float`, *optional*, defaults to `1/255`): Scale factor to use if rescaling the image. Only has an effect if `do_rescale` is set to `True`. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`float` or `List[float]`, *optional*, defaults to `IMAGENET_STANDARD_MEAN`): Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_mean` parameter in the `preprocess` method. Can be overridden by the `image_mean` parameter in the `preprocess` method. image_std (`float` or `List[float]`, *optional*, defaults to `IMAGENET_STANDARD_STD`): Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_std` parameter in the `preprocess` method. Can be overridden by the `image_std` parameter in the `preprocess` method. do_center_crop (`bool`, *optional*, defaults to `True`): Whether to center crop the image. Can be overridden by the `do_center_crop` parameter in the `preprocess` method. crop_size (`Dict[str, int]`, *optional*): Desired output size when applying center-cropping. Only has an effect if `do_center_crop` is set to `True`. Can be overridden by the `crop_size` parameter in the `preprocess` method. If unset defaults to `size`, do_pad (`bool`, *optional*, defaults to `True`): Whether to pad the image to the `(max_height, max_width)` of the images in the batch. Can be overridden by the `do_pad` parameter in the `preprocess` method. pixel_valuesTN gp? do_resizesizerIresample do_rescalerescale_factor do_normalize image_mean image_stddo_center_crop crop_sizedo_padr$c  @d| vr| jd} t|di| ||nddi}t|d}||_||_||_||_||_||_ ||_ ||nt|_ | | nt|_| |_| |_| |_y)Npad_and_return_pixel_mask shortest_edgei Fdefault_to_square)popsuper__init__r rWrXrIrYrZr[r\rr]rr^rar_r`)selfrWrXrIrYrZr[r\r]r^r_r`rakwargs __class__s r)rjz"BridgeTowerImageProcessor.__init__s '& 0ZZ ;*DT&/&; ,"r:r+ data_formatr-c t|d}d|vrtd|j|d}td|z} t ||| ||} t |f| |||d|S)a Resize an image. Resizes the shorter side of the image to `size["shortest_edge"]` while preserving the aspect ratio. If the longer side is larger than the max size `(int(`size["shortest_edge"]` * 1333 / 800))`, the longer side is then resized to the max size while preserving the aspect ratio. Args: image (`np.ndarray`): Image to resize. size (`Dict[str, int]`): Controls the size of the output image. Should be of the form `{"shortest_edge": int}`. size_divisor (`int`, *optional*, defaults to 32): The image is resized to a size that is a multiple of this value. resample (`PILImageResampling` filter, *optional*, defaults to `PILImageResampling.BICUBIC`): Resampling filter to use when resiizing the image. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. Frerdz@The `size` dictionary must contain the key `shortest_edge`. Got g)\?)rGrHrIr-)rXrYrnr-)r r@keysrLrRr) rkr+rXrIrYrnr-rlrGrHr,s r)rz BridgeTowerImageProcessor.resizes>TU; $ &_`d`i`i`k_lmn n'Z')*2 76 `q   #/     r:c 0|d}t|f||f||d|S)a" Center crop an image to `(size["height"], size["width"])`. If the input size is smaller than `crop_size` along any edge, the image is padded with 0's and then center cropped. Args: image (`np.ndarray`): Image to center crop. size (`Dict[str, int]`): Size of the output image in the form `{"height": h, "width": w}`. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred from the input image. rd)rXrnr-)r)rkr+rXrnr-rlr,s r)rz%BridgeTowerImageProcessor.center_crops;.?+   {+#/     r:r,constant_valuesct||\}}|\}} ||z } | |z } d| fd| ff} t|| tj|||} | S)z< Pad an image with zeros to the given size. r/r)moderrrnr-)rrrCONSTANT)rkr+r,rrrnr-r6r7 output_height output_width pad_bottom pad_rightpadding padded_images r) _pad_imagez$BridgeTowerImageProcessor._pad_image"sp%35FW$X! k&1# |"\1  ;. z?Q N3  %%+#/  r:r;return_pixel_maskreturn_tensorsc t||}|Dcgc]}|j|||||} }d| i} |r |Dcgc]}t|||} }| | d<t| |Scc}wcc}w)a Pads a batch of images to the bottom and right of the image with zeros to the size of largest height and width in the batch and optionally returns their corresponding pixel mask. Args: image (`np.ndarray`): Image to pad. constant_values (`float` or `Iterable[float]`, *optional*): The value to use for the padding if `mode` is `"constant"`. return_pixel_mask (`bool`, *optional*, defaults to `True`): Whether to return a pixel mask. return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. Can be one of: - Unset: Return a list of `np.ndarray`. - `TensorType.TENSORFLOW` or `'tf'`: Return a batch of type `tf.Tensor`. - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`. - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`. - `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. )r-)rrrnr-rU)r+r,r- pixel_maskdata tensor_type)rEr|r9r ) rkr;rrr}r~rnr-pad_sizer+ padded_imagesrmaskss r)rzBridgeTowerImageProcessor.pad>s@(BST    OO /'"3      . $ eUfgE"'D >BB'  s A$A)c||n |j}||n |j}||n |j}||n |j}||n |j}||n |j }| | n |j } | | n |j} | | n |j} | | n |j| | n#|j |jn |j} ||n |j}t|d}t|s|g}t|s tdt!|||| | | || | ||| |Dcgc] }t#|}}t%|dr|rt&j)d|r#|Dcgc]}|j+|||||}}| r!|Dcgc]}|j-|| |}}|r!|Dcgc]}|j/||| }}|r"|Dcgc]}|j1|| | | }}|Dcgc]}t3||| }}| r|j5|d || }|St7d|i|}|Scc}wcc}wcc}wcc}wcc}wcc}w)ah Preprocess an image or batch of images. Args: images (`ImageInput`): Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. do_resize (`bool`, *optional*, defaults to `self.do_resize`): Whether to resize the image. size (`Dict[str, int]`, *optional*, defaults to `self.size`): Controls the size of the image after `resize`. The shortest edge of the image is resized to `size["shortest_edge"]` whilst preserving the aspect ratio. If the longest edge of this resized image is > `int(size["shortest_edge"] * (1333 / 800))`, then the image is resized again to make the longest edge equal to `int(size["shortest_edge"] * (1333 / 800))`. size_divisor (`int`, *optional*, defaults to `self.size_divisor`): The image is resized to a size that is a multiple of this value. resample (`PILImageResampling`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the image. Only has an effect if `do_resize` is set to `True`. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image values between [0 - 1]. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to rescale the image by if `do_rescale` is set to `True`. do_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether to normalize the image. image_mean (`float` or `List[float]`, *optional*, defaults to `self.image_mean`): Image mean to normalize the image by if `do_normalize` is set to `True`. image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`): Image standard deviation to normalize the image by if `do_normalize` is set to `True`. do_pad (`bool`, *optional*, defaults to `self.do_pad`): Whether to pad the image to the (max_height, max_width) in the batch. If `True`, a pixel mask is also created and returned. do_center_crop (`bool`, *optional*, defaults to `self.do_center_crop`): Whether to center crop the image. If the input size is smaller than `crop_size` along any edge, the image is padded with 0's and then center cropped. crop_size (`Dict[str, int]`, *optional*, defaults to `self.crop_size`): Size of the image after center crop. If one edge the image is smaller than `crop_size`, it will be padded with zeros and then cropped return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. Can be one of: - Unset: Return a list of `np.ndarray`. - `TensorType.TENSORFLOW` or `'tf'`: Return a batch of type `tf.Tensor`. - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`. - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`. - `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`. data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`): The channel dimension format for the output image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - Unset: Use the channel dimension format of the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. FrezkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.) rZr[r\r]r^rasize_divisibilityr_r`rWrXrYrzIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r+rXrIrYr-)r+rXr-)r+rOr-)r+meanstdr-)input_channel_dimT)r}r~r-rUr)rWrIrYrZr[r\r]r^rar_r`rXr rrr@rrrlogger warning_oncerrrescale normalizerrr )rkr;rWrXrIrYrZr[r\r]r^rar_r`r~rnr-r+encoded_outputss r) preprocessz$BridgeTowerImageProcessor.preprocessusX"+!6IDNN '3'?|TEVEV '38#-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN !-4;;(4$:M:M#.It~~GaT^^gkgpgp 'tTYYTU;&!XFF#:  &!)%!*) 6<9=#$("#"#38n"# "# % "#  "#c5j)"#"#U5$u+#567"#E%e"456"#"#S>"#"# "#R'9'A'A>BDH. zz. 38n.  . % . eC)9$9:; . $E#/?*?$@A.  . h?CDH  zz 38n eC)9$9:;  $E#/?*?$@A    J:;26DH zz38_uhuo56  ./  $E#/?*?$@A  >:;"&;?26DH5CRZZ 5Cuhuo565C 5C !sJ!78 5C ./ 5C$E#/?*?$@A5C 5Cn%&%))-&*'+%)*.'+:>9=!%)-$(;?(8(>(>DH#ffD>ftCH~& f sm f % fTNf!ftnfU5$u+#567fE%e"456ff!fS>f!sJ!78f &!f"$E#/?*?$@A#f$ %f'fr:rT)N)i i5rVN)3rtypingrrrrrrr numpyr3image_processing_utilsr r r image_transformsrrrrr image_utilsrrrrrrrrrrrrutilsrr r!r"r get_loggerrrr*rrLrr9rErRrTrgr:r)rs|-DDDUUbb    _^   H %8x}8c8rv ::$)#s(OHPQVWZ\lWlQmHnZZ([_#  #19%EU@U:V1W# #Y#*@D !! ! ! !  c+;&; <= !  38_ !>` 2`r: