bCi;SrSSKJrJr SSKrSSKJrJrJ r SSK J r J r J r SSKJrJrJrJrJrJrJrJrJrJrJr SSKJrJrJrJr \"5(aSSKr\R@"\!5r""S S \5r#S /r$g) zImage processor class for BLIP.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbresizeto_channel_dimension_format) OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingc^\rSrSrSrS/rSS\RSSSSSS4 S\S\ \ \ \ 4S \S \S \ \ \4S \S \ \ \\\4S\ \ \\\4S\SS4U4Sjjjr\RSS4S\R$S\ \ \ 4S \S\ \ \ \4S\ \ \ \4S\R$4 Sjjr\"5SSSSSSSSSS\R,S4 S\S\ \S\ \ \ \ 4S \ \S \ \S \ \S \ \S \ \ \\\4S\ \ \\\4S\ \ \ \4S\ \S\S\ \ \ \4S\R4R44Sjj5rSrU=r$)BlipImageProcessor.a[ Constructs a BLIP 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`, *optional*, defaults to `{"height": 384, "width": 384}`): Size of the output image after resizing. Can be overridden by the `size` 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_convert_rgb (`bool`, *optional*, defaults to `True`): Whether to convert the image to RGB. pixel_valuesTNgp? do_resizesizeresample do_rescalerescale_factor do_normalize image_mean image_stddo_convert_rgbreturnc  >[T U]"S0U D6 UbUOSSS.n[USS9nXlX lX0lX@lXPlX`lUbUO[Ul UbUO[Ul Xl g)Ni)heightwidthTdefault_to_square)super__init__rrr r!r"r#r$r r%r r&r') selfrr r!r"r#r$r%r&r'kwargs __class__s h/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/blip/image_processing_blip.pyr0BlipImageProcessor.__init__Ssu "6"'tc-JTT:"  $,((2(>*DT&/&;,image data_formatinput_data_formatc [U5nSU;dSU;a[SUR535eUSUS4n[U4UUUUS.UD6$)a Resize an image to `(size["height"], size["width"])`. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BICUBIC`. data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. 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. 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. Returns: `np.ndarray`: The resized image. r*r+zFThe `size` dictionary must contain the keys `height` and `width`. Got )r r!r8r9)r ValueErrorkeysr )r1r7r r!r8r9r2 output_sizes r4r BlipImageProcessor.resizeosyFT" 4 7$#6efjfofofqerst tH~tG}5   #/     r6imagesreturn_tensorsc FUbUO URnUbUO URnUbUO URnUbUO URnUbUO URnUbUO UR nU bU O UR n U bU O URn UbUO URn[USS9nURU5n[U5n[U5(d [S5e[UUUUU UUUS9 U (aUVs/sHn[U5PM nnUVs/sHn[!U5PM nnU(a([#US5(a[$R'S5 U c[)US5n U(a UVs/sHnUR+XXMS9PM nnU(a UVs/sHnUR-XU S9PM nnU(a UVs/sHnUR/XXS 9PM nnUVs/sH n[1XU S 9PM nn[3S U0U S 9nU$s snfs snfs snfs snfs snfs snf) a 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))`. 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_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`): Whether to convert the image to RGB. 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. Fr,zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)r"r#r$r%r&rr r!rzIt 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.)r7r r!r9)r7scaler9)r7meanstdr9)input_channel_dimr)data tensor_type)rr!r"r#r$r%r&r'r r fetch_imagesrrr;rr rrlogger warning_oncerr rescale normalizer r)r1r?rr r!r"r#r$r%r&r@r'r8r9r7encoded_outputss r4 preprocessBlipImageProcessor.preprocesssu@"+!6IDNN '38#-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN +9+E4K^K^'tTYYTU;""6*)&1F##:  &!)%!  9?@nU+F@6<vay I  $#E %X k#  $#E 5Rc d#  $#EUp#  ou ntej 'N_ `nt  '^V,DR`aOA=    s$6HH 3HHH!H) r'r$r"rr%r&r!r#r )__name__ __module__ __qualname____firstlineno____doc__model_input_namesrBICUBICboolrdictstrintrfloatlistr0npndarrayrr rFIRSTrrPILImagerN__static_attributes__ __classcell__)r3s@r4rr.s D(()-'9'A'A,3!:>9=#--tCH~&-% -  - c5j) --U5$u+#567-E%e"456-- --@(:'A'A>BDH . zz. 38n. % . eC)9$9:; . $E#/?*?$@A .  . `%&%))-15%)*.'+:>9=;?)-(8(>(>DHFFD>FtCH~& F -. F TN F!FtnFU5$u+#567FE%e"456F!sJ!78F!F&F$E#/?*?$@AF F'Fr6r)%rTtypingrrnumpyr]image_processing_utilsrrrimage_transformsr r r image_utilsr r rrrrrrrrrutilsrrrrr` get_loggerrPrIr__all__r.r6r4rlss&"UUSS    _^   H %x+xv r6