cCiX nSrSSKJr SSKJrJr SSKrSSKJ r J r J r SSK J r JrJrJrJr SSKJrJrJrJrJrJrJrJrJrJr SS KJrJrJ r J!r! \ "5(aSSK"r"\!RF"\$5r%S \&\&\4S jr'SS \RPS \)S\\\*\4S \+\)\)44Sjjr,"SS\ 5r-S/r.g)zImage processor class for TVP.)Iterable)OptionalUnionN)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_availableloggingreturncJ[U[[45(a6[US[[45(a[USS5(aU$[U[[45(a[US5(aU/$[U5(aU//$[ SU35e)Nrz"Could not make batched video from ) isinstancelisttupler ValueError)videoss f/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/tvp/image_processing_tvp.py make_batchedr%5s&4-((Zq D%=-Q-QVdeklmenopeqVrVr FT5M * *~fQi/H/Hx   z 9&B CC input_imagemax_sizeinput_data_formatc[X5up4X4:aUS-U- nUnXe-nOUS-U- nUnXu-n[U5[U54nU$)Ng?)rint) r'r(r)heightwidthratio new_height new_widthsizes r$get_resize_output_image_sizer2Bsb #;BMF  f$ &  u$ &  OS^ ,D Kr&c+t^\rSrSrSrS/rSS\RSSSSSSS\RSSSS4S\ S \ \ \ \4S \S \ S \ \ \ \4S \ S\\\4S\ S\ \ \ \4S\\\\4S\S\ S\ S\ \\\\4S\ \\\\4SS4 U4Sjjjr\RSS4S\R*S \ \ \4S \S\ \\ \4S\ \\ \4S\R*4 SjjrSS\RSS4S\R*S\ \ \ \4S\\\\4S\S\ \\ \4S\ \\ \44 SjjrSSSSSSSSSSSSSSS\R2S4S\S\ \ S \ \ \ \4S \ \S \ \ S \ \ \ \4S \ \ S\ \S\ S\ \ \ \4S\ \\\\4S\ \S\ \ S\ \ S\ \\\\4S\ \\\\4S\ \S\ \\ \4S\R*4&Sjjr\"5SSSSSSSSSSSSSSSS\R2S4S\\\\\\\4S\ \ S \ \ \ \4S \ \S \ \ S \ \ \ \4S \ \ S\ \S\ \ S\ \ \ \4S\ \\\\4S\ \S\ \ S\ \ S\ \\\\4S\ \\\\4S \ \\ \4S\S\ \\ \4S\R>R>4(S!jj5r S"r!U=r"$)#TvpImageProcessorUa@ 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_resizer1resampledo_center_crop crop_size do_rescalerescale_factordo_padpad_sizeconstant_valuespad_mode do_normalizedo_flip_channel_order image_mean image_stdrc F>[TU]"S0UD6 UbUOSS0nUbUOSSS.nU bU OSSS.n XlX lX@lXPlX0lX`lXplXl Xl Xl Xl Xl XlUbUO[UlUbXlg["Ulg)N longest_edge)r,r-)super__init__r7r1r9r:r8r;r<r=r>r?r@rArBrrCrrD)selfr7r1r8r9r:r;r<r=r>r?r@rArBrCrDkwargs __class__s r$rJTvpImageProcessor.__init__s& "6"'tnc-B!*!6IsUX*DZ&/&;AVr&image data_formatr)c [USS9nSU;aSU;a USUS4nO2SU;a[XSU5nO[SUR535e[ U4UUUUS.UD6$)a} Resize an image. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Size of the output image. If `size` is of the form `{"height": h, "width": w}`, the output image will have the size `(h, w)`. If `size` is of the form `{"longest_edge": s}`, the output image will have its longest edge of length `s` while keeping the aspect ratio of the original image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`): Resampling filter to use when resiizing the image. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. Fdefault_to_squarer,r-rFzCSize must have 'height' and 'width' or 'longest_edge' as keys. Got )r1r8rPr))r r2r"keysr )rKrOr1r8rPr)rL output_sizes r$r TvpImageProcessor.resizes4TU; t 4>4=9K t #6u>>RTefKbcgclclcnbopq q  #/     r&c [XS9upURSU5n URSU 5n X- X- pU S:dU S:a [S5eSU 4SU 44n[UUUUUUS9nU$)a Pad an image with zeros to the given size. Args: image (`np.ndarray`): Image to pad. pad_size (`dict[str, int]`) Size of the output image with pad. constant_values (`Union[float, Iterable[float]]`) The fill value to use when padding the image. pad_mode (`PaddingMode`) The pad mode, default to PaddingMode.CONSTANT data_format (`ChannelDimension` or `str`, *optional*) The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. ) channel_dimr,r-rz0The padding size must be greater than image size)moder?rPr))rgetr"r )rKrOr>r?r@rPr)rLr,r- max_height max_width pad_right pad_bottompadding padded_images r$ pad_imageTvpImageProcessor.pad_images6'uL \\(F3 LL%0 ) 1:3F: q=JNOP Pz?Q N3  +#/  r&c [UUU UUUUUUUS9 [U5nU(aURXUUS9nU(aURXUS9nU(aUR XUS9nU (a/UR UR [R5UUUS9nU (aURUU U U US9nU(a [UUS9n[UUUS9nU$) zPreprocesses a single image.) r;r<rArCrDr9r:r7r1r8)rOr1r8r))r1r))rOscaler))rOmeanstdr))rOr>r?r@r))rOr))input_channel_dim) rrr center_croprescale normalizeastypenpfloat32rar r)rKrOr7r1r8r9r:r;r<r=r>r?r@rArBrCrDrPr)rLs r$_preprocess_image#TvpImageProcessor._preprocess_image s0 &!)%!) u% KKe]nKoE $$UN_$`E LLuVgLhE NNll2::.ZYbs#E NN! /!"3 #E !&UFWXE+E;Rcd r&r#return_tensorsc\UbUO URnUbUO URnUbUO URnUbUO URnUbUO URnU bU O UR n U bU O UR n U bU O URn U (aU O URn U bU O URn UbUO URnUbUO URnUbUO URnUbUO URn[USS9nUbUO URn[USS9n[!U5(d [#S5e[%U5nUVVs/sHHn[&R("UVs/sH#nUR+UUUUUUUUU U U U U UUUUUS9PM% sn5PMJ nnnSU0n[-UUS9$s snfs snnf) a 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. FrRr:) param_namezkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)rOr7r1r8r9r:r;r<r=r>r?r@rArBrCrDrPr)r6)data tensor_type)r7r8r9r;r<r=r>r?r@rArBrCrDr1r r:rr"r%rlarrayrnr)rKr#r7r1r8r9r:r;r<r=r>r?r@rArBrCrDrprPr)videoimgrss r$ preprocessTvpImageProcessor.preprocessRs`"+!6IDNN '38+9+E4K^K^#-#9Zt +9+E4K^K^!-4;;'38-<-H/dNbNb'8T]]'3'?|TEVEV %:%F !DLfLf $.#9Zt !*!6IDNN 'tTYYTU;!*!6IDNN !) D F##:  f%8 5 4 3 HH, %+* %)**!"+!!)'5"+#-'5%!)(7!)%1.C#-"+$/*;%+( %+ 2 5  :'>BB9 sF(*F# F(#F()r?r:r9rBrAr=r;r7rCrDr@r>r8r<r1)#__name__ __module__ __qualname____firstlineno____doc__model_input_namesrBILINEARr CONSTANTboolrdictstrr+rfloatrr rJrlndarrayrr raFIRSTrrnrrPILImagerx__static_attributes__ __classcell__)rMs@r$r4r4UsB/b(()-'9'B'B#.2,3-19: + 4 4!&*:>9=!&W&WtCH~&&W% &W  &W DcN+ &W&Wc5j)&W&W4S>*&Wuhuo56&W&W&W $&WU5$u+#567&W E%e"456!&W$ %&W&WX(:'B'B>BDH ) zz) 38n) % ) eC)9$9:; ) $E#/?*?$@A )  ) \.29: + 4 4>BDH-zz-4S>*-uhuo56 -  - eC)9$9:; -$E#/?*?$@A-d%))-15)-.2%)*.-1CG*.'+04:>9=2B2H2HDH'EED>EtCH~& E -. E ! EDcN+ETNE!EE4S>*E"%x(>"?@E;'EtnE (~E U5$u+#567!E"E%e"456#E$./%E&$E#/?*?$@A'E* +EN%&%))-15)-.2%)*.!%-1CG*.'+04:>9=;?(8(>(>DH)JCj$z"2Dj9I4JJKJCD>JCtCH~& JC -. JC ! JCDcN+JCTNJC!JCJC4S>*JC"%x(>"?@JC;'JCtnJC (~JC U5$u+#567!JC"E%e"456#JC$!sJ!78%JC&&'JC($E#/?*?$@A)JC* +JC'JCr&r4)rGN)/r~collections.abcrtypingrrnumpyrlimage_processing_utilsrrr image_transformsr r r r r image_utilsrrrrrrrrrrutilsrrrrr get_loggerrzloggerr r%rr+rr!r2r4__all__rHr&r$rs%$"UU   _^   H % DDj!12 D@D c+;&; <= 38_ &HC*HCV  r&