o
    Zh;                     @   s   d Z ddlmZmZmZmZ ddlZddlm	Z	m
Z
mZ ddlmZmZ ddlmZmZmZmZmZmZmZmZmZmZmZ ddlmZmZmZmZ dd	l m!Z! e rWddl"Z"e#e$Z%e!d
dG dd de	Z&dgZ'dS )zImage processor class for DeiT.    )DictListOptionalUnionN   )BaseImageProcessorBatchFeatureget_size_dict)resizeto_channel_dimension_format)IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension
ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_arrayvalid_imagesvalidate_preprocess_arguments)
TensorTypefilter_out_non_signature_kwargsis_vision_availablelogging)requires)Zvision)backendsc                       s  e Zd ZdZdgZddejjdddddddf
dede	e
eef  ded	ed
e	e
eef  deeef dedede	eeee f  de	eeee f  ddf fddZejddfdejde
eef dede	eeef  de	eeef  dejfddZe dddddddddddejdfdede	e de	e
eef  d	e	e d
e	e
eef  de	e de	e de	e de	eeee f  de	eeee f  de	eeef  dede	eeef  dejjfddZ  ZS )DeiTImageProcessora	  
    Constructs a DeiT 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": 256, "width": 256}`):
            Size of the image after `resize`. Can be overridden by `size` in `preprocess`.
        resample (`PILImageResampling` filter, *optional*, defaults to `Resampling.BICUBIC`):
            Resampling filter to use if resizing the image. Can be overridden by `resample` in `preprocess`.
        do_center_crop (`bool`, *optional*, defaults to `True`):
            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": 224, "width": 224}`):
            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.
        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.
    pixel_valuesTNgp?	do_resizesizeresampledo_center_crop	crop_sizerescale_factor
do_rescaledo_normalize
image_mean	image_stdreturnc                    s   t  jdi | |d ur|nddd}t|}|d ur|nddd}t|dd}|| _|| _|| _|| _|| _|| _|| _	|| _
|	d urG|	nt| _|
d urS|
| _d S t| _d S )N   )heightwidth   r#   
param_name )super__init__r	   r   r    r!   r"   r#   r%   r$   r&   r   r'   r   r(   )selfr   r    r!   r"   r#   r$   r%   r&   r'   r(   kwargs	__class__r0   ]/var/www/auris/lib/python3.10/site-packages/transformers/models/deit/image_processing_deit.pyr2   T   s   zDeiTImageProcessor.__init__imagedata_formatinput_data_formatc                 K   sT   t |}d|vsd|vrtd|  |d |d f}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!   r9   r:   )r	   
ValueErrorkeysr
   )r3   r8   r    r!   r9   r:   r4   Zoutput_sizer0   r0   r7   r
   t   s   #zDeiTImageProcessor.resizeimagesreturn_tensorsc                    s  |dur|n| j }|dur|n| j}|dur|n| j}|dur!|n| j}|dur*|n| j}|	dur3|	n| j}	|
dur<|
n| j}
|durE|n| j}|durN|n| j}t	|}|dur[|n| j
}t	|dd}t|}t|sptdt|||	|
||||||d
 dd |D }|rt|d rtd	 du rt|d g }|D ]1}|r| j|||d
}|r| j||d}|r| j||d}|	r| j||
|d}|| q fdd|D }d|i}t||dS )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`.
            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:
                    - `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.
        Nr#   r.   zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)
r%   r$   r&   r'   r(   r"   r#   r   r    r!   c                 S   s   g | ]}t |qS r0   )r   .0r8   r0   r0   r7   
<listcomp>  s    z1DeiTImageProcessor.preprocess.<locals>.<listcomp>r   zIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r8   r    r!   r:   )r8   r    r:   )r8   scaler:   )r8   meanZstdr:   c                    s   g | ]	}t | d qS ))Zinput_channel_dim)r   r?   r9   r:   r0   r7   rA   $  s    r   )dataZtensor_type)r   r!   r"   r%   r$   r&   r'   r(   r    r	   r#   r   r   r;   r   r   loggerZwarning_oncer   r
   Zcenter_cropZrescale	normalizeappendr   )r3   r=   r   r    r!   r"   r#   r%   r$   r&   r'   r(   r>   r9   r:   Z
all_imagesr8   rE   r0   rD   r7   
preprocess   sl   AzDeiTImageProcessor.preprocess)__name__
__module____qualname____doc__Zmodel_input_namesPILZImageZBICUBICboolr   r   strintr   r   floatr   r2   npZndarrayr   r
   r   ZFIRSTr   r   rI   __classcell__r0   r0   r5   r7   r   /   s    !
	
$

0	
r   )(rM   typingr   r   r   r   numpyrS   Zimage_processing_utilsr   r   r	   Zimage_transformsr
   r   Zimage_utilsr   r   r   r   r   r   r   r   r   r   r   utilsr   r   r   r   Zutils.import_utilsr   rN   Z
get_loggerrJ   rF   r   __all__r0   r0   r0   r7   <module>   s   4
 
~