`ibAdZddlmZddlmZmZddlZddlm Z m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZmZmZdd lmZmZmZdd l m!Z!ej"e#Z$e!d Gd de Z%dgZ&dS)z Image processor class for LeViT.)Iterable)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)get_resize_output_image_sizeresizeto_channel_dimension_format) IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargslogging)requires)vision)backendsc!eZdZdZdgZddejdddddeef de de e e e fded e d e e e e fd e d ee efd e de eeeefde eeeefddffd Zejddfdejde e e fdede ee efde ee efdejf dZedddddddddddejdf dede e de e e e fde ed e e d e e e e fd e e d e ed e e de eeeefde eeeefde edede ee efdefdZxZS)LevitImageProcessora Constructs a LeViT image processor. Args: do_resize (`bool`, *optional*, defaults to `True`): Wwhether to resize the shortest edge of the input to int(256/224 *`size`). Can be overridden by the `do_resize` parameter in the `preprocess` method. size (`dict[str, int]`, *optional*, defaults to `{"shortest_edge": 224}`): Size of the output image after resizing. If size is a dict with keys "width" and "height", the image will be resized to `(size["height"], size["width"])`. If size is a dict with key "shortest_edge", the shortest edge value `c` is rescaled to `int(c * (256/224))`. The smaller edge of the image will be matched to this value i.e, if height > width, then image will be rescaled to `(size["shortest_edge"] * height / width, size["shortest_edge"])`. 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. Can be overridden by the `resample` parameter in the `preprocess` method. do_center_crop (`bool`, *optional*, defaults to `True`): Whether or not to center crop the input to `(crop_size["height"], crop_size["width"])`. Can be overridden by the `do_center_crop` parameter in the `preprocess` method. crop_size (`Dict`, *optional*, defaults to `{"height": 224, "width": 224}`): Desired image size after `center_crop`. Can be overridden by the `crop_size` parameter in the `preprocess` method. do_rescale (`bool`, *optional*, defaults to `True`): Controls 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`): Controls whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`list[int]`, *optional*, defaults to `[0.485, 0.456, 0.406]`): 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 (`list[int]`, *optional*, defaults to `[0.229, 0.224, 0.225]`): 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_resizesizeresampledo_center_crop crop_size do_rescalerescale_factor do_normalize image_mean image_stdreturnc  Ptjdi| ||nddi}t|d}||nddd}t|d}||_||_||_||_||_||_||_ ||_ | | nt|_ | | nt|_dS) N shortest_edgeFdefault_to_squareheightwidthr% param_name)super__init__r r!r"r#r$r%r&r'r(r r)rr*) selfr!r"r#r$r%r&r'r(r)r*kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/levit/image_processing_levit.pyr8zLevitImageProcessor.__init__[s ""6"""'ttos-CTU;;;!*!6IIsUX**DY&/&;AUimage data_formatinput_data_formatc <t|d}d|vr width, then image will be rescaled to `(size["shortest_edge"] * height / width, size["shortest_edge"])`. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Size of the output image after resizing. If size is a dict with keys "width" and "height", the image will be resized to (height, width). If size is a dict with key "shortest_edge", the shortest edge value `c` is rescaled to int(`c` * (256/224)). The smaller edge of the image will be matched to this value i.e, if height > width, then image will be rescaled to (size * height / width, size). resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): Resampling filter to use when resiizing the image. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. Fr/r-g$I$I?)r"r0r@rr1r2r3zFSize dict must have keys 'height' and 'width' or 'shortest_edge'. Got )r"r#r?r@)r intr ValueErrorkeysr ) r9r>r"r#r?r@r: size_dictr- output_sizes r<r zLevitImageProcessor.resizezsD"$%@@@ d " "d?.C CDDM6MUVgK$/q>KNKKI 9 $ $y(@(@kYbYgYgYiYikk   H%y'9:#/       r=imagesreturn_tensorsc D ||nj}nj||nj}||nj}nj| | nj}  nj  nj njtdnj tdt|}t|stdt|| || d|D}|r/t|d rt d t%|d |rfd |D}|rfd |D}|rfd |D}| r fd|D} fd|D}d|i}t'|| S)a Preprocess an image or batch of images to be used as input to a LeViT model. Args: images (`ImageInput`): Image or batch of images 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 output image after resizing. If size is a dict with keys "width" and "height", the image will be resized to (height, width). If size is a dict with key "shortest_edge", the shortest edge value `c` is rescaled to int(`c` * (256/224)). The smaller edge of the image will be matched to this value i.e, if height > width, then image will be rescaled to (size * height / width, size). resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): Resampling filter to use when resiizing the image. 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 output image after center cropping. Crops images to (crop_size["height"], crop_size["width"]). do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image pixel values by `rescaling_factor` - typical to values between 0 and 1. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Factor to rescale the image pixel values by. do_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether to normalize the image pixel values by `image_mean` and `image_std`. image_mean (`float` or `list[float]`, *optional*, defaults to `self.image_mean`): Mean to normalize the image pixel values by. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`): Standard deviation to normalize the image pixel values by. 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*, defaults to `ChannelDimension.FIRST`): 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. 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. NFr/r%r4zkInvalid 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#c,g|]}t|Sr6)r).0r>s r< z2LevitImageProcessor.preprocess..s <<r@r#r9r"s r<rMz2LevitImageProcessor.preprocess..#s/rrrbgdkk%xK\k]]rrrr=c@g|]}|SrO) center_crop)rLr>r%r@r9s r<rMz2LevitImageProcessor.preprocess..&s0rrrbgd&&uiK\&]]rrrr=c@g|]}|SrO)rescale)rLr>r@r'r9s r<rMz2LevitImageProcessor.preprocess..)s-ssschdll5.L]l^^sssr=cBg|]}|SrO) normalize)rLr>r)r*r@r9s r<rMz2LevitImageProcessor.preprocess..,s;fkuj)O`aar=c4g|]}t|S))input_channel_dim)r )rLr>r?r@s r<rMz2LevitImageProcessor.preprocess..0s7   ej '{N_ ` ` `   r=r )data tensor_type)r!r#r$r&r'r(r)r*r"r r%rrrDrrlogger warning_oncerr)r9rHr!r"r#r$r%r&r'r(r)r*rIr?r@rXs` `` ` ` `` `` r< preprocesszLevitImageProcessor.preprocesssH"+!6IIDN '388+9+E4K^#-#9ZZt +9+E4K^'3'?||TEV #-#9ZZt !*!6IIDN 'ttTYTU;;;!*!6IIDN !) DDD )&11F## :  &!)%!) =vay I I   srrrrrrrkqrrrF  srrrrrrkqrrrF  tsssssslrsssF  ouF     nt   '>BBBBr=)__name__ __module__ __qualname____doc__model_input_namesrBICUBICr rboolrdictstrrCrfloatrr8npndarrayrr rFIRSTrrrr\ __classcell__)r;s@r<rr0s_%%N(()-'9'A#.2,3!>S=QVVVtCH~&V% V  V DcN+ VVc5j)VVU5(5/#9:;VE%%"89:V VVVVVVF(:'A>BDH 5 5 z5 38n5 % 5 eC)9$9:; 5 $E#/?*?$@A 5  5 5 5 5 n%$&&%))-15)-.2%)*.'+>B=A/3(8(>DHCCCCCCD>CCtCH~& CC -. CC ! CCDcN+CCTNCC!CCtnCCU5(5/#9:;CCE%%"89:CC!,CC&CC$E#/?*?$@ACC !CCCCCC'&CCCCCCCCCCr=r)'r`collections.abcrtypingrrnumpyrgimage_processing_utilsrrr image_transformsr r r image_utilsr rrrrrrrrrrutilsrrrutils.import_utilsr get_loggerr]rZr__all__r6r=r<rus'&$$$$$$""""""""UUUUUUUUUU                          JIIIIIIIII******  H % % ;DCDCDCDCDC,DCDC DCN ! !r=