T^(h8dZddlmZmZmZmZddlZddlm Z m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZej@e!Z"Gd d e Z#d gZ$y) zImage processor class for ViT.)DictListOptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsloggingcPeZdZdZdgZddej ddddddf dedee e e fded ed e e e fd ed ee e ee fd ee e ee fdeeddffd Zej ddfdej"de e e fdedee e efdee e efdej"f dZedddddddddej*ddf dedeede e e fded eed ee d eed ee e ee fd ee e ee fdee e efde e efdee e efdeefdZxZS)ViTImageProcessorax Constructs a ViT image processor. Args: do_resize (`bool`, *optional*, defaults to `True`): Whether to resize the image's (height, width) dimensions to the specified `(size["height"], size["width"])`. Can be overridden by the `do_resize` parameter in the `preprocess` method. size (`dict`, *optional*, defaults to `{"height": 224, "width": 224}`): Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): Resampling filter to use if resizing the image. 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. 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. 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. 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. do_convert_rgb (`bool`, *optional*): Whether to convert the image to RGB. pixel_valuesTNgp? do_resizesizeresample do_rescalerescale_factor do_normalize image_mean image_stddo_convert_rgbreturnc  t |di| ||nddd}t|}||_||_||_||_||_||_||nt|_ ||nt|_ | |_ y)N)heightwidth)super__init__r rr"r$r r!r#rr%rr&r') selfrr r!r"r#r$r%r&r'kwargs __class__s j/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/vit/image_processing_vit.pyr/zViTImageProcessor.__init__Ms "6"'tc-JT""$(   ,(2(>*DZ&/&;AV,image data_formatinput_data_formatc t|}d|vsd|vrtd|j|d|df}t|f||||d|S)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.BILINEAR`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BILINEAR`. 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!r6r7)r ValueErrorkeysr )r0r5r r!r6r7r1 output_sizes r3r zViTImageProcessor.resizegsyFT" 4 7$#6efjfofofqerst tH~tG}5   #/     r4imagesreturn_tensorsc ||n |j}||n |j}||n |j}||n |j}||n |j}||n |j }| | n |j } | | n |j} ||n |j}t|}t|}t|s tdt||||| |||| r|Dcgc] }t|}}|Dcgc] }t|}}|r#t!|drt"j%d| t'|d} |r"|Dcgc]}|j)|||| }}|r!|Dcgc]}|j+||| }}|r"|Dcgc]}|j-||| | }}|Dcgc]}t/|| | }}d |i}t1|| Scc}wcc}wcc}wcc}wcc}wcc}w) aa 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`): Dictionary in the format `{"height": h, "width": w}` specifying the size of the output image after resizing. resample (`PILImageResampling` filter, *optional*, defaults to `self.resample`): `PILImageResampling` filter to use if resizing the image e.g. `PILImageResampling.BILINEAR`. 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 use if `do_normalize` is set to `True`. image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`): Image standard deviation to use if `do_normalize` is set to `True`. 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. do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`): Whether to convert the image to RGB. 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.)r5r r!r7)r5scaler7)r5meanstdr7)input_channel_dimr)data tensor_type)rr"r$r!r#r%r&r'r r rrr9rr rrlogger warning_oncerr rescale normalizer r )r0r<rr r!r"r#r$r%r&r=r6r7r' size_dictr5rCs r3 preprocesszViTImageProcessor.preprocesss[~"+!6IDNN #-#9Zt '3'?|TEVEV '38+9+E4K^K^#-#9Zt !*!6IDNN +9+E4K^K^'tTYY!$' $V,F#:  &!)%!  9?@nU+@F@6<vay I  $ %i(^o pF $ 5Rc dF $U^opF ou ej '{N_ `  '>BBMA=    s$G.G=G!GG"&G')__name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrrstrintrfloatrr/npndarrayrr rFIRSTrrrJ __classcell__)r2s@r3rr*s@(()-'9'B'B,3!:>9=)---tCH~&-% -  - c5j) --U5$u+#567-E%e"456-!- -<(:'B'B>BDH . zz. 38n. % . eC)9$9:; . $E#/?*?$@A .  . `%&%)#'+%)*.'+:>9=;?4D4J4JDH)-CCCCD>CC38n CC % CC TN CC!CCtnCCU5$u+#567CCE%e"456CC!sJ!78CC3 001CC$E#/?*?$@ACC!CC'CCr4r)%rNtypingrrrrnumpyrUimage_processing_utilsrr r image_transformsr r r image_utilsrrrrrrrrrrrutilsrrr get_loggerrKrEr__all__r-r4r3rasl%..UUSS    JI   H %qC*qCh  r4