S^(hGdZddlmZmZmZmZddlZddlm Z m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZm Z erddl!Z!e jDe#Z$Gd d e Z%d gZ&y) z'Image processor class for EfficientNet.)DictListOptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)rescaleresizeto_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_kwargsis_vision_availableloggingc#eZdZdZdgZddej jdddddddddf dede e e fd e d ed e e e fd e e efd edededee eeefdee eeefdeddffd Ze jddfdej&de e e fd e dee e efdee e efdej&f dZ ddej&de e efdedee e efdee e eff dZedddddddddddddej0dfdedeede e e fd eed e e e fdeed eed eedeedee eeefdee eeefdeedee e efdedee e efdej j f dZxZS) EfficientNetImageProcessoraN Constructs a EfficientNet 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 `do_resize` in `preprocess`. size (`Dict[str, int]` *optional*, defaults to `{"height": 346, "width": 346}`): Size of the image after `resize`. Can be overridden by `size` in `preprocess`. resample (`PILImageResampling` filter, *optional*, defaults to 0): Resampling filter to use if resizing the image. Can be overridden by `resample` in `preprocess`. do_center_crop (`bool`, *optional*, defaults to `False`): 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. Can be overridden by `do_center_crop` in `preprocess`. crop_size (`Dict[str, int]`, *optional*, defaults to `{"height": 289, "width": 289}`): Desired output size when applying center-cropping. Can be overridden by `crop_size` in `preprocess`. 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. rescale_offset (`bool`, *optional*, defaults to `False`): Whether to rescale the image between [-scale_range, scale_range] instead of [0, scale_range]. Can be overridden by the `rescale_factor` 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. 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. include_top (`bool`, *optional*, defaults to `True`): Whether to rescale the image again. Should be set to True if the inputs are used for image classification. pixel_valuesTNFgp? do_resizesizeresampledo_center_crop crop_sizerescale_factorrescale_offset do_rescale do_normalize image_mean image_std include_topreturnc  @t|di| ||nddd}t|}||nddd}t|d}||_||_||_||_||_||_||_ ||_ | |_ | | nt|_ | | nt|_| |_y)NiZ)heightwidthi!r$ param_name)super__init__r r r!r"r#r$r'r%r&r(rr)rr*r+)selfr r!r"r#r$r%r&r'r(r)r*r+kwargs __class__s |/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/efficientnet/image_processing_efficientnet.pyr4z#EfficientNetImageProcessor.__init__Ws "6"'tc-JT"!*!6IsUX*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.NEAREST`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.NEAREST`. 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 )r5r:r!r"r;r<r6 output_sizes r8r z!EfficientNetImageProcessor.resize{syFT" 4 7$#6efjfofofqerst tH~tG}5   #/     r9scaleoffsetc 4t|f|||d|}|r|dz }|S)a Rescale an image by a scale factor. If `offset` is `True`, the image has its values rescaled by `scale` and then offset by 1. If `scale` is 1/127.5, the image is rescaled between [-1, 1]. image = image * scale - 1 If `offset` is `False`, and `scale` is 1/255, the image is rescaled between [0, 1]. image = image * scale Args: image (`np.ndarray`): Image to rescale. scale (`int` or `float`): Scale to apply to the image. offset (`bool`, *optional*): Whether to scale the image in both negative and positive directions. 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. )rAr;r<)r )r5r:rArBr;r<r6rescaled_images r8r z"EfficientNetImageProcessor.rescales;>!  KK\ `f  +a/Nr9imagesreturn_tensorsc ||n |j}||n |j}||n |j}||n |j}||n |j}| | n |j } | | n |j } | | n |j} | | n |j} | | n |j} ||n |j}t|}||n |j}t|d}t|}t|s tdt!||| | | ||||| |Dcgc] }t#|}}|r#t%|drt&j)d|t+|d}|r"|Dcgc]}|j-||||}}|r!|Dcgc]}|j/|||}}|r"|Dcgc]}|j1||| | }}| r"|Dcgc]}|j3|| | | }}| r"|Dcgc]}|j3|d| | }}|Dcgc]}t5||| }}d |i}t7|| Scc}wcc}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_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 `resize`. resample (`PILImageResampling`, *optional*, defaults to `self.resample`): PILImageResampling filter to use if resizing the image Only has an effect if `do_resize` is set to `True`. do_center_crop (`bool`, *optional*, defaults to `self.do_center_crop`): Whether to center crop the image. 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 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`. rescale_offset (`bool`, *optional*, defaults to `self.rescale_offset`): Whether to rescale the image between [-scale_range, scale_range] instead of [0, scale_range]. 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. include_top (`bool`, *optional*, defaults to `self.include_top`): Rescales the image again for image classification if set to True. return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. Can be one of: - `None`: 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$r r!r"rzIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r:r!r"r<)r:r!r<)r:rArBr<)r:meanstdr<)input_channel_dimr)data tensor_type)r r"r#r'r%r&r(r)r*r+r!r r$rrr>rrrlogger warning_oncerr center_cropr normalizer r )r5rFr r!r"r#r$r'r%r&r(r)r*r+rGr;r<r:rLs r8 preprocessz%EfficientNetImageProcessor.preprocesssN"+!6IDNN '38+9+E4K^K^#-#9Zt +9+E4K^K^+9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN %0%vay I  $ %dXYj kF pvgl  u9Pa bF  $  ~n`qF $U^opF $U UfgF ou ej '{N_ `  '>BBa=     s*H;"II)I  I1II)TNN)__name__ __module__ __qualname____doc__model_input_namesPILImageNEARESTboolrstrintrrfloatrrr4npndarrayrr r rFIRSTrrrR __classcell__)r7s@r8rr.s~$L((#'*yy'8'8$$(,3$!:>9= !'!'38n!'% !'  !' S> !'c5j)!'!'!'!'U5$u+#567!'E%e"456!'!' !'P(:'A'A>BDH . zz. 38n. % . eC)9$9:; . $E#/?*?$@A .  . h>BDH &zz&S%Z & & eC)9$9:; & $E#/?*?$@A &P%&%)#)-$(%)*.)-'+:>9=&*;?(8(>(>DH#ZCZCD>ZC38n ZC ! ZCS>ZCTNZC!ZC!ZCtnZCU5$u+#567ZCE%e"456ZCd^ZC!sJ!78ZC &!ZC"$E#/?*?$@A#ZC$ %ZC'ZCr9r)'rVtypingrrrrnumpyr_image_processing_utilsrr r image_transformsr r r image_utilsrrrrrrrrrrrutilsrrrrrX get_loggerrSrNr__all__r2r9r8rksw...UULL    _^   H %@C!3@CF ( (r9