T^(hPDdZddlmZmZmZmZddlZddlm Z m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZmZmZmZddlmZmZm Z m!Z!e rddl"Z"e!jFe$Z%Gd d e Z&d gZ'y) z$Image processor class for Perceiver.)DictListOptionalUnionN)BaseImageProcessor BatchFeature get_size_dict) center_cropresizeto_channel_dimension_format) IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_STDChannelDimension ImageInputPILImageResamplingget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingc!eZdZdZdgZddddej dddddf dedee e fded ee e fd ed ed e e e fd ede e e ee fde e e ee fddffd Z ddej"dee e fd e e de e e efde e e efdej"f dZej ddfdej"d ee e fd ede e e efde e e efdej"f dZedddddddddddej,df dede ede ee e fde ed e ee e fd ed e ed e e d e ede e e ee fde e e ee fde e e efdede e e efdej4j4fdZxZS)PerceiverImageProcessora/ Constructs a Perceiver image processor. Args: do_center_crop (`bool`, `optional`, defaults to `True`): Whether or not to center crop the image. If the input size if smaller than `crop_size` along any edge, the image will be padded with zeros and then center cropped. Can be overridden by the `do_center_crop` parameter in the `preprocess` method. crop_size (`Dict[str, int]`, *optional*, defaults to `{"height": 256, "width": 256}`): Desired output size when applying center-cropping. Can be overridden by the `crop_size` parameter in the `preprocess` method. do_resize (`bool`, *optional*, defaults to `True`): Whether to resize the image to `(size["height"], size["width"])`. Can be overridden by the `do_resize` parameter in the `preprocess` method. size (`Dict[str, int]` *optional*, defaults to `{"height": 224, "width": 224}`): Size of the image after resizing. Can be overridden by the `size` parameter in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): Defines the 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`): Defines the scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. do_normalize: 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. pixel_valuesTNgp?do_center_crop crop_size do_resizesizeresample do_rescalerescale_factor do_normalize image_mean image_stdreturnc  0t |di| ||nddd}t|d}||nddd}t|}||_||_||_||_||_||_||_ ||_ | | nt|_ | | |_yt|_y)N)heightwidthr" param_name)super__init__r r!r"r#r$r%r&r'r(rr)rr*) selfr!r"r#r$r%r&r'r(r)r*kwargs __class__s v/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/perceiver/image_processing_perceiver.pyr5z PerceiverImageProcessor.__init__Vs "6"!*!6IsUX*DY&/&;AUimage data_formatinput_data_formatc | |jn|}t|}t|d}t||\}}t||} |d|dz | z} |d|dz | z} t |f| | f||d|S)a Center crop an image to `(size["height"] / crop_size["height"] * min_dim, size["width"] / crop_size["width"] * min_dim)`. Where `min_dim = min(size["height"], size["width"])`. If the input size is smaller than `crop_size` along any edge, the image will be padded with zeros and then center cropped. Args: image (`np.ndarray`): Image to center crop. crop_size (`Dict[str, int]`): Desired output size after applying the center crop. size (`Dict[str, int]`, *optional*): Size of the image after resizing. If not provided, the self.size attribute will be used. 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. r"r0) channel_dimr.r/)r$r<r=)r$r rminr ) r6r;r"r$r<r=r7r.r/min_dimcropped_height cropped_widths r9r z#PerceiverImageProcessor.center_cropus8!LtyydT"!) D &u:KL fe$x.9X+>>'Ig7);;wF    -0#/     r:c 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.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$r%r<r=)r ValueErrorkeysr )r6r;r$r%r<r=r7 output_sizes r9r zPerceiverImageProcessor.resizesyFT" 4 7$#6efjfofofqerst tH~tG}5   #/     r:imagesreturn_tensorsc *||n |j}||n |j}t|d}||n |j}||n |j}t|}||n |j }||n |j }||n |j}| | n |j} | | n |j} | | n |j} t|}t|s tdt||| | | ||||| |Dcgc] }t|}}|r#t!|drt"j%d|t'|d}|r"|Dcgc]}|j)||||}}|r"|Dcgc]}|j+||||}}|r!|Dcgc]}|j-||| }}| r"|Dcgc]}|j/|| | | }}|Dcgc]}t1|| | }}d |i}t3|| Scc}wcc}wcc}wcc}wcc}wcc}w)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_center_crop (`bool`, *optional*, defaults to `self.do_center_crop`): Whether to center crop the image to `crop_size`. crop_size (`Dict[str, int]`, *optional*, defaults to `self.crop_size`): Desired output size after applying the center crop. do_resize (`bool`, *optional*, defaults to `self.do_resize`): Whether to resize the image. size (`Dict[str, int]`, *optional*, defaults to `self.size`): Size of the image after resizing. resample (`int`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the image. This can be one of the enum `PILImageResampling`, 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. 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. image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`): Image standard deviation. 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: - `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `ChannelDimension.LAST`: image in (height, width, num_channels) 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. r"r0zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.) r&r'r(r)r*r!r"r#r$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.)r$r=)r;r$r%r=)r;scaler=)r;meanstdr=)input_channel_dimr )data tensor_type)r!r"r r#r$r%r&r'r(r)r*rrrErrrlogger warning_oncerr r rescale normalizer r )r6rHr!r"r#r$r%r&r'r(r)r*rIr<r=r;rOs r9 preprocessz"PerceiverImageProcessor.preprocesss@,:+E4K^K^!*!6IDNN !) D !*!6IDNN 'tTYYT"'38#-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN $V,F#:  &!)%!) 6<vay I  pvgl   Pa bF $ %dXYj kF $ 5Rc dF $U^opF ou ej '{N_ `  '>BBQ=     s$3G7G<&H H-H H)NNN)__name__ __module__ __qualname____doc__model_input_namesrBICUBICboolrstrintrfloatrrr5npndarrayrr r rFIRSTrrPILImagerU __classcell__)r8s@r9rr/sm"H(( $$(#'9'A'A,3!:>9=VVS>V V 38n V % VVc5j)VVU5$u+#567VE%e"456V VF#>BDH * zz* S>* sm * eC)9$9:; * $E#/?*?$@A *  * b(:'A'A>BDH . zz. 38n. % . eC)9$9:; . $E#/?*?$@A .  . `%&*..2$()-'+%)*.'+:>9=;?(8(>(>DHICIC!ICDcN+ IC D> IC tCH~& IC%ICTNIC!ICtnICU5$u+#567ICE%e"456IC!sJ!78IC&IC$E#/?*?$@AIC !IC'ICr:r)(rYtypingrrrrnumpyr`image_processing_utilsrr r image_transformsr r r image_utilsrrrrrrrrrrrrutilsrrrrrc get_loggerrVrQr__all__r3r:r9rnsw+..UUPP    _^   H %mC0mC` % %r: