o Zh1Y @s"dZddlmZmZmZmZmZmZddlZ ddl m Z m Z m Z ddlmZmZmZmZmZddlmZmZmZmZmZmZmZmZmZmZddlm Z m!Z!m"Z"m#Z#e"rYddl$Z$e#%e&Z'd eeefd d Z( dd e j)de*deee+efd ee*e*ffddZ,Gddde Z-dgZ.dS)zImage processor class for TVP.)DictIterableListOptionalTupleUnionN)BaseImageProcessor BatchFeature get_size_dict) PaddingModeflip_channel_orderpadresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplingget_image_sizeis_valid_imageto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingreturncCsrt|ttfrt|dttfrt|ddr|St|ttfr*t|dr*|gSt|r2|ggStd|)Nrz"Could not make batched video from ) isinstancelisttupler ValueError)videosr%[/var/www/auris/lib/python3.10/site-packages/transformers/models/tvp/image_processing_tvp.py make_batched4s0r' input_imagemax_sizeinput_data_formatc Cs\t||\}}||kr|d|}|}||}n |d|}|}||}t|t|f}|S)Ng?)rint) r)r*r+heightwidthratioZ new_heightZ new_widthsizer%r%r&get_resize_output_image_sizeAs   r1c+seZdZdZdgZddejdddddddejddddfde de e e e fd ed e d e e e e fd e d ee efde de e e e fdeeeefdede de de eeeefde eeeefddf fdd Zejddfdejde e e fd ede ee efde ee efdejf ddZddejddfdejde e e e fdeeeefdede ee efde ee eff ddZdddddddddddddddejdfdede e de e e e fd ed e e d e e e e fd e e d e ede de e e e fde eeeefdede e de e de eeeefde eeeefde ede ee efdejf&d d!Zeddddddddddddddddejdfd"eeeeeeefde e de e e e fd ed e e d e e e e fd e e d e ede e de e e e fde eeeefdede e de e de eeeefde eeeefd#e ee efdede ee efdejjf(d$d%ZZ S)&TvpImageProcessora Constructs a Tvp 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 the `do_resize` parameter in the `preprocess` method. size (`Dict[str, int]` *optional*, defaults to `{"longest_edge": 448}`): Size of the output image after resizing. The longest edge of the image will be resized to `size["longest_edge"]` while maintaining the aspect ratio of the original image. Can be overridden by `size` 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_center_crop (`bool`, *optional*, defaults to `True`): Whether to center crop the image to the specified `crop_size`. Can be overridden by the `do_center_crop` parameter in the `preprocess` method. crop_size (`Dict[str, int]`, *optional*, defaults to `{"height": 448, "width": 448}`): Size of the image after applying the center crop. Can be overridden by the `crop_size` 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_pad (`bool`, *optional*, defaults to `True`): Whether to pad the image. Can be overridden by the `do_pad` parameter in the `preprocess` method. pad_size (`Dict[str, int]`, *optional*, defaults to `{"height": 448, "width": 448}`): Size of the image after applying the padding. Can be overridden by the `pad_size` parameter in the `preprocess` method. constant_values (`Union[float, Iterable[float]]`, *optional*, defaults to 0): The fill value to use when padding the image. pad_mode (`PaddingMode`, *optional*, defaults to `PaddingMode.CONSTANT`): Use what kind of mode in padding. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. do_flip_channel_order (`bool`, *optional*, defaults to `True`): Whether to flip the color channels from RGB to BGR. Can be overridden by the `do_flip_channel_order` 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?r do_resizer0resampledo_center_crop crop_size do_rescalerescale_factordo_padpad_sizeconstant_valuespad_mode do_normalizedo_flip_channel_order image_mean image_stdrc stjdi||dur|nddi}|dur|nddd}| dur$| nddd} ||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_|durV|nt|_|durb||_dSt|_dS)N longest_edger()r-r.r%)super__init__r4r0r6r7r5r8r9r:r;r<r=r>r?rr@rrA)selfr4r0r5r6r7r8r9r:r;r<r=r>r?r@rAkwargs __class__r%r&rDs&zTvpImageProcessor.__init__image data_formatr+cKstt|dd}d|vrd|vr|d|df}nd|vr$t||d|}n td|t|f||||d|S)a Resize an image. Args: image (`np.ndarray`): Image to resize. size (`Dict[str, int]`): Size of the output image. If `size` is of the form `{"height": h, "width": w}`, the output image will have the size `(h, w)`. If `size` is of the form `{"longest_edge": s}`, the output image will have its longest edge of length `s` while keeping the aspect ratio of the original image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`): 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 (`str` or `ChannelDimension`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. FZdefault_to_squarer-r.rBzCSize must have 'height' and 'width' or 'longest_edge' as keys. Got )r0r5rJr+)r r1r#keysr)rErIr0r5rJr+rFZ output_sizer%r%r&rs zTvpImageProcessor.resizecKszt||d\}} |d|} |d| } | | | |} } | dks%| dkr)tdd| fd| ff}t||||||d}|S)a+ Pad an image with zeros to the given size. Args: image (`np.ndarray`): Image to pad. pad_size (`Dict[str, int]`) Size of the output image with pad. constant_values (`Union[float, Iterable[float]]`) The fill value to use when padding the image. pad_mode (`PaddingMode`) The pad mode, default to PaddingMode.CONSTANT data_format (`ChannelDimension` or `str`, *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. )Z channel_dimr-r.rz0The padding size must be greater than image size)moder<rJr+)rgetr#r)rErIr;r<r=rJr+rFr-r. max_height max_width pad_rightZ pad_bottompaddingZ padded_imager%r%r& pad_images    zTvpImageProcessor.pad_imagecKst||| ||| | |||||d t|}|r|j||||d}|r)|j|||d}|r3|j|||d}| rB|j|tj|||d}| rN|j || | | |d}|rVt ||d}t |||d}|S) zPreprocesses a single image.) r8r9r>r@rAr:Zsize_divisibilityr6r7r4r0r5)rIr0r5r+)r0r+)rIscaler+)rImeanZstdr+)rIr;r<r=r+)rIr+)Zinput_channel_dim) rrrZ center_cropZrescale normalizeZastypenpZfloat32rSr r)rErIr4r0r5r6r7r8r9r:r;r<r=r>r?r@rArJr+rFr%r%r&_preprocess_image sJ z#TvpImageProcessor._preprocess_imager$return_tensorscsdurnjdurnjdurnjdur!njdur*njdur3nj dur< nj durEnj rL nj durUnj dur^nj  durg nj durp nj durynj tdddurnjtddt|stdt|} fdd|D}d |i}t||d S) a9 Preprocess an image or batch of images. Args: videos (`ImageInput` or `List[ImageInput]` or `List[List[ImageInput]]`): Frames to preprocess. 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 applying resize. resample (`PILImageResampling`, *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_center_crop (`bool`, *optional*, defaults to `self.do_centre_crop`): Whether to centre crop the image. crop_size (`Dict[str, int]`, *optional*, defaults to `self.crop_size`): Size of the image after applying the centre crop. 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_pad (`bool`, *optional*, defaults to `True`): Whether to pad the image. Can be overridden by the `do_pad` parameter in the `preprocess` method. pad_size (`Dict[str, int]`, *optional*, defaults to `{"height": 448, "width": 448}`): Size of the image after applying the padding. Can be overridden by the `pad_size` parameter in the `preprocess` method. constant_values (`Union[float, Iterable[float]]`, *optional*, defaults to 0): The fill value to use when padding the image. pad_mode (`PaddingMode`, *optional*, defaults to "PaddingMode.CONSTANT"): Use what kind of mode in padding. do_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether to normalize the image. do_flip_channel_order (`bool`, *optional*, defaults to `self.do_flip_channel_order`): Whether to flip the channel order of 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. - Unset: Use the inferred 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. NFrKr7) param_namezkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.csFg|]}t fdd|DqS)csg|]>}jdid|ddddddddd d d d d d d dd qS)rIr4r0r5r6r7r8r9r:r;r<r=r>r?r@rArJr+r%)rX).0Zimgr<r7rJr6r?r>r:r8r4r@rAr+r=r;r5r9rEr0r%r& sP      z;TvpImageProcessor.preprocess...)rWarray)r[Zvideor\r%r&r]s,z0TvpImageProcessor.preprocess..r3)dataZ tensor_type)r4r5r6r8r9r:r;r<r=r>r?r@rAr0r r7rr#r'r )rEr$r4r0r5r6r7r8r9r:r;r<r=r>r?r@rArYrJr+r_r%r\r& preprocessSs8P  , zTvpImageProcessor.preprocess)!__name__ __module__ __qualname____doc__Zmodel_input_namesrZBILINEARr ZCONSTANTboolrrstrr,rfloatrrrDrWndarrayrrrSZFIRSTrrXrrPILZImager` __classcell__r%r%rGr&r2Ts1      ,  . 2      I     r2)r(N)/rdtypingrrrrrrnumpyrWZimage_processing_utilsr r r Zimage_transformsr r rrrZ image_utilsrrrrrrrrrrutilsrrrrriZ get_loggerraloggerr'rhr,rfr1r2__all__r%r%r%r&s6 0