qyiHSrSSKrSSKJr SSKJr SSKJrJ r J r SSK J r J r JrJr SSKJrJrJrJrJrJrJrJrJrJrJr SS KJrJr \"5(aSSKr\R@"\!5r"S \#\#\4S jr$"S S \5r%S /r&g)z Image processor class for Vivit.N)is_vision_available) TensorType)BaseImageProcessor BatchFeature get_size_dict)get_resize_output_image_sizerescaleresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imageis_valid_imageto_numpy_array valid_imagesvalidate_preprocess_arguments)filter_out_non_signature_kwargsloggingreturncJ[U[[45(a6[US[[45(a[USS5(aU$[U[[45(a[US5(aU/$[U5(aU//$[ SU35e)Nrz"Could not make batched video from ) isinstancelisttupler ValueError)videoss m/home/mande/repo/quber/.venv/lib/python3.13/site-packages/transformers/models/vivit/image_processing_vivit.py make_batchedr"2s&4-((Zq D%=-Q-QVdeklmenopeqVrVr FT5M * *~fQi/H/Hx   z 9&B CCc"^\rSrSrSrS/rSS\RSSSSSSSS4 S\S\ \ \ 4S-S \S \S \ \ \ 4S-S \S \ \ -S\S\S\ \ \ -S-S\ \ \ -S-SS4U4Sjjjr\RSS4S\R S\ \ \ 4S \S\ \-S-S\ \-S-S\R 4 SjjrSS\R S\ \ -S\S\ \-S-S\ \-S-4 SjjrSSSSSSSSSSS\R(S4 S\S\S-S\ \ \ 4S-S \S-S \S-S \ \ \ 4S-S \S-S \ S-S\S-S\S-S\ \ \ -S-S\ \ \ -S-S\S-S\ \-S-S\R 4Sjjr\"5SSSSSSSSSSSS\R(S4S\S\S-S\ \ \ 4S-S \S-S \S-S \ \ \ 4S-S \S-S \ S-S\S-S\S-S\ \ \ -S-S\ \ \ -S-S\ \-S-S\S\ \-S-S\R4R44 Sjj5rSrU=r$) VivitImageProcessor?a Constructs a Vivit 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 `{"shortest_edge": 256}`): Size of the output image after resizing. The shortest edge of the image will be resized to `size["shortest_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": 224, "width": 224}`): 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 `1/127.5`): Defines the scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. offset (`bool`, *optional*, defaults to `True`): Whether to scale the image in both negative and positive directions. Can be overridden by the `offset` 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? do_resizesizeresampledo_center_crop crop_size do_rescalerescale_factoroffset do_normalize image_mean image_stdrc  *>[T U]"S 0U D6 UbUOSS0n[USS9nUbUOSSS.n[USS9nXlX lX@lXPlX0lX`lXpl Xl Xl U bU O[Ul U bXlg[Ulg) N shortest_edgeFdefault_to_square)heightwidthr, param_name)super__init__rr(r)r+r,r*r-r.r/r0r r1rr2)selfr(r)r*r+r,r-r.r/r0r1r2kwargs __class__s r!r?VivitImageProcessor.__init__js "6"'tos-CTU;!*!6IsUX*DZ&/&;AVr#image data_formatinput_data_formatc [USS9nSU;a[XSSUS9nO3SU;aSU;a USUS4nO[SUR535e[ U4UUUUS.UD6$) 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 `{"shortest_edge": s}`, the output image will have its shortest 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. Fr6r4)r7rFr9r:zDSize must have 'height' and 'width' or 'shortest_edge' as keys. Got )r)r*rErF)rr rkeysr )r@rDr)r*rErFrA output_sizes r!r VivitImageProcessor.resizes4TU; d "6O,YjK 'T/>4=9Kcdhdmdmdocpqr r  #/     r#scalec <[U4X$US.UD6nU(aUS- nU$)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. )rKrErF)r )r@rDrKr/rErFrArescaled_images r!r VivitImageProcessor.rescales9>!  K\ `f  +a/Nr#c [UUU U U UUUUUS9 U (aU(d [S5e[U5nU(a%[U5(a[R S5 Uc [ U5nU(aURXXNS9nU(aURXUS9nU(aURXXS9nU (aURXXS9n[XUS9nU$) zPreprocesses a single image.) r-r.r0r1r2r+r,r(r)r*z0For offset, do_rescale must also be set to True.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.)rDr)r*rF)r)rF)rDrKr/rF)rDmeanstdrF)input_channel_dim) rrrrlogger warning_oncerr center_cropr normalizer )r@rDr(r)r*r+r,r-r.r/r0r1r2rErFs r!_preprocess_image%VivitImageProcessor._preprocess_images& &!)%!)  *OP Pu% /%00   s   $ >u E  KKeKoE $$UN_$`E LLu6LwE NNYNtE+ERcd r#r return_tensorscUbUO URnUbUO URnUbUO URnUbUO URnUbUO URnU bU O UR n U bU O UR n U bU O URn U bU O URn UbUO URn[USS9nUbUO URn[USS9n[U5(d [S5e[U5nUVVs/sH0nUVs/sHnURUUUUUUUUU U U U UUS9PM! snPM2 nnnSU0n[!UU S9$s snfs snnf) a Preprocess an image or batch of images. Args: videos (`ImageInput`): Video frames to preprocess. Expects a single or batch of video frames with pixel values ranging from 0 to 255. If passing in frames 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 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 `[-1 - 1]` if `offset` is `True`, `[0, 1]` otherwise. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to rescale the image by if `do_rescale` is set to `True`. offset (`bool`, *optional*, defaults to `self.offset`): Whether to scale the image in both negative and positive directions. 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.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`. - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.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. Fr6r,r;zSInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.Tensor)rDr(r)r*r+r,r-r.r/r0r1r2rErFr')data tensor_type)r(r*r+r-r.r/r0r1r2r)rr,rrr"rXr)r@r r(r)r*r+r,r-r.r/r0r1r2rZrErFvideoimgr\s r! preprocessVivitImageProcessor.preprocesssD"+!6IDNN '38+9+E4K^K^#-#9Zt +9+E4K^K^!-4;;'3'?|TEVEV #-#9Zt !*!6IDNN 'tTYYTU;!*!6IDNN !) D F##rs sf%, ) ( !# "!C!&&'%#1')#1!!-)' +&7' !# & )  .'>BB/  s; E&E +EE) r,r+r0r-r(r1r2r/r*r.r))TNN)__name__ __module__ __qualname____firstlineno____doc__model_input_namesrBILINEARbooldictstrintfloatrr?npndarrayrr r FIRSTrrXrrPILImager`__static_attributes__ __classcell__)rBs@r!r%r%?s&P((&*'9'B'B#+/&/!1504WW38nt#W% W  W S>D( WWe WWWDK'$.W4;&-W WWJ(:'B'B59;? * zz* 38n* % * ++d2 * !11D8 *  * `59;? &zz&U{& & ++d2 & !11D8 &V"&&*.2&*+/"&'+"$(1504/?/E/E;?<<$;<38nt# < %t+ < t <S>D(<4K< <t <Tk<DK'$.<4;&-<&,<!11D8< !<|%&"&&*.2&*+/"&'+"$(150426(8(>(>;?!mCmC$;mC38nt# mC %t+ mC t mCS>D(mC4KmC mCt mCTkmCDK'$.mC4;&-mCj(4/mC&mC !11D8!mC" #mC'mCr#r%)'rfnumpyrntransformers.utilsrtransformers.utils.genericrimage_processing_utilsrrrimage_transformsr r r r image_utilsr rrrrrrrrrrutilsrrrq get_loggerrbrTrr"r%__all__r=r#r!r~s'21UU    >   H % DDj!12 DLC,LC^ ! !r#