cCiA,SrSSKJrJr SSKrSSKJrJrJ r SSK J r J r J r SSKJrJrJrJrJrJrJrJrJrJrJr SSKJrJrJrJr SS KJ r \"5(aSSK!r!\RD"\#5r$S \%\%\4S jr&\ "S S 9"SS\55r'S/r(g)z#Image processor class for VideoMAE.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)get_resize_output_image_sizeresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imageis_valid_imageto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availablelogging)requiresreturncJ[U[[45(a6[US[[45(a[USS5(aU$[U[[45(a[US5(aU/$[U5(aU//$[ SU35e)Nrz"Could not make batched video from ) isinstancelisttupler ValueError)videoss p/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/videomae/image_processing_videomae.py make_batchedr$3s&4-((Zq D%=-Q-QVdeklmenopeqVrVr FT5M * *~fQi/H/Hx   z 9&B CC)vision)backendsc!^\rSrSrSrS/rSS\RSSSSSSS4 S\S\ \ \ \ 4S \S \S \ \ \ \ 4S \S \ \ \4S\S\ \ \\\4S\ \ \\\4SS4U4Sjjjr\RSS4S\R$S\ \ \ 4S \S\ \ \ \4S\ \ \ \4S\R$4 SjjrSSSSSSSSSS\R*S4 S\S\ \S\ \ \ \ 4S \ \S \ \S \ \ \ \ 4S \ \S \ \S\ \S\ \ \\\4S\ \ \\\4S\ \S\ \ \ \4S\R$4Sjjr\"5SSSSSSSSSSS\R*S4 S\S\ \S\ \ \ \ 4S \ \S \ \S \ \ \ \ 4S \ \S \ \S\ \S\ \ \\\4S\ \ \\\4S\ \ \ \4S\S\ \ \ \4S\R6R64Sjj5rSrU=r$)VideoMAEImageProcessor@a Constructs a VideoMAE 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": 224}`): 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 `1/255`): Defines the 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`): 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_valuesTNgp? do_resizesizeresampledo_center_crop crop_size do_rescalerescale_factor do_normalize image_mean image_stdrc  >[T U]"S0U D6 UbUOSS0n[USS9nUbUOSSS.n[USS9nXlX lX@lXPlX0lX`lXpl Xl U bU O[Ul U bXlg[Ulg) N shortest_edgeFdefault_to_square)heightwidthr0 param_name)super__init__rr,r-r/r0r.r1r2r3r r4r r5) selfr,r-r.r/r0r1r2r3r4r5kwargs __class__s r#rAVideoMAEImageProcessor.__init__is "6"'tos-CTU;!*!6IsUX*DZ&/&;AVr%image data_formatinput_data_formatc [USS9nSU;a[XSSUS9nO3SU;aSU;a USUS4nO[SUR535e[ U4UUUUS.UD6$) a Resize an image. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Size of the output image. If `size` is of the form `{"height": h, "width": w}`, the output image will have the size `(h, w)`. If `size` is of the form `{"shortest_edge": s}`, the output image will have its shortest edge of length `s` while keeping the aspect ratio of the original image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`): Resampling filter to use when resiizing the image. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. Fr9r7)r:rHr;r<zDSize must have 'height' and 'width' or 'shortest_edge' as keys. Got )r-r.rGrH)rr r!keysr )rBrFr-r.rGrHrC output_sizes r#r VideoMAEImageProcessor.resizes4TU; d "6O,YjK 'T/>4=9Kcdhdmdmdocpqr r  #/     r%c [UUU U U UUUUUS9 [U5nU(a%[U5(a[R S5 U c [ U5n U(aUR XXMS9nU(aURXU S9nU(aURXU S9nU (aURXXS9n[XU S9nU$)zPreprocesses a single image.) r1r2r3r4r5r/r0r,r-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.)rFr-r.rH)r-rH)rFscalerH)rFmeanstdrH)input_channel_dim) rrrlogger warning_oncerr center_croprescale normalizer )rBrFr,r-r.r/r0r1r2r3r4r5rGrHs r#_preprocess_image(VideoMAEImageProcessor._preprocess_images" &!)%!) u% /%00   s   $ >u E  KKeKoE $$UN_$`E LLuVgLhE NNYNtE+ERcd r%r"return_tensorscxUbUO URnUbUO URnUbUO URnUbUO URnUbUO URnU bU O UR n U bU O UR n U bU O URn UbUO URn[USS9nUbUO URn[USS9n[U5(d [S5e[U5nUVVs/sH/nUVs/sHnURUUUUUUUUU U U U US9 PM snPM1 nnnSU0n[UU S9$s snfs snnf) 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 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_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.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. Fr9r0r=zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.) rFr,r-r.r/r0r1r2r3r4r5rGrHr+)data tensor_type)r,r.r/r1r2r3r4r5r-rr0rr!r$rWr)rBr"r,r-r.r/r0r1r2r3r4r5rYrGrHvideoimgr[s r# preprocess!VideoMAEImageProcessor.preprocesssB"+!6IDNN '38+9+E4K^K^#-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN 'tTYYTU;!*!6IDNN !) D F##:  f%* ' & !!  !C&&'%#1')#1!-)' +&7'!! $ '  ,'>BB-  s* D64%D1 D61D6) r0r/r3r1r,r4r5r.r2r-)__name__ __module__ __qualname____firstlineno____doc__model_input_namesrBILINEARboolrdictstrintrfloatrrAnpndarrayrr FIRSTrrWrrPILImager___static_attributes__ __classcell__)rDs@r#r)r)@s4#J(()-'9'B'B#.2,3!:>9=WWtCH~&W% W  W DcN+ WWc5j)WWU5$u+#567WE%e"456W WWF(:'B'B>BDH * zz* 38n* % * eC)9$9:; * $E#/?*?$@A *  * ^%))-15)-.2%)*.'+:>9=2B2H2HDH77D>7tCH~& 7 -. 7 ! 7DcN+7TN7!7tn7U5$u+#5677E%e"4567./7$E#/?*?$@A7 7r%&%))-15)-.2%)*.'+:>9=;?(8(>(>DHmCmCD>mCtCH~& mC -. mC ! mCDcN+mCTNmC!mCtnmCU5$u+#567mCE%e"456mC!sJ!78mC&mC$E#/?*?$@AmC !mC'mCr%r)))retypingrrnumpyrmimage_processing_utilsrrrimage_transformsr r r image_utilsr r rrrrrrrrrutilsrrrrutils.import_utilsrrp get_loggerrarRrr$r)__all__r?r%r#r}s*"UU    _^*   H % DDj!12 D ;ZC/ZC ZCz $ $r%