cCi\6SrSSKJrJr SSKrSSKJrJrJ r SSK J r J r J r Jr SSKJrJrJrJrJrJrJrJrJr SSKJrJrJrJrJrJr SS K J!r! \"5(aSSK"r"\"5(aSSK#r#\RH"\%5r&\!"S S 9"S S \55r'S /r(g)z$Image processor class for MobileViT.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)flip_channel_orderget_resize_output_image_sizeresizeto_channel_dimension_format) ChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_torch_availableis_torch_tensoris_vision_availablelogging)requires)vision)backendsc!^\rSrSrSrS/rSS\RSSSSSS4 S\S \ \ \ \ 4S \S \S \ \ \4S \S\ \ \ \ 4S\S\SS4U4Sjjjr\RSS4S\R"S \ \ \ 4S \S\ \ \ \4S\ \ \ \4S\R"4 SjjrS&S\R"S\ \ \ \4S\ \ \ \4S\R"4SjjrS\S\R"4SjrS'U4SjjrS(S\S\S\S \S \S\S \ \ \ \ 4S \ \S \ \S\ \ \ \ 4S\ \ \ \44SjjrS)S\S\ \S \ \ \ \ 4S \ \S \ \S \ \S \ \S\ \ \ \ 4S\ \S\ \ \ \4S\ \ \ \4S\R"4SjjrS*S\S\ \S\ \S \ \ \ \ 4S \ \S\ \ \ \ 4S\ \ \ \4S\R"4Sjjr\"5SSSSSSSSSSS\R8S4 S\S \ \S\ \S \ \ \ \ 4S \ \S \ \S \ \S \ \S\ \ \ \ 4S\ \S\ \S!\ \ \ \4S\S\ \ \ \4S\R>R>4S"jj5r S'S#\ \!\"4S$jjr#S%r$U=r%$)+MobileViTImageProcessor7ad Constructs a MobileViT 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}`): Controls the size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): Defines the resampling filter to use if resizing the image. Can be overridden by the `resample` 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`): Scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. do_center_crop (`bool`, *optional*, defaults to `True`): Whether to crop the input at the center. 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 the `do_center_crop` parameter in the `preprocess` method. crop_size (`dict[str, int]`, *optional*, defaults to `{"height": 256, "width": 256}`): Desired output size `(size["height"], size["width"])` when applying center-cropping. Can be overridden by the `crop_size` 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. do_reduce_labels (`bool`, *optional*, defaults to `False`): Whether or not to reduce all label values of segmentation maps by 1. Usually used for datasets where 0 is used for background, and background itself is not included in all classes of a dataset (e.g. ADE20k). The background label will be replaced by 255. Can be overridden by the `do_reduce_labels` parameter in the `preprocess` method. pixel_valuesTNgp?F do_resizesizeresample do_rescalerescale_factordo_center_crop crop_sizedo_flip_channel_orderdo_reduce_labelsreturnc  >[T U]"S 0U D6 UbUOSS0n[USS9nUbUOSSS.n[USS9nXlX lX0lX@lXPlX`lXpl Xl Xl g) N shortest_edgeFdefault_to_square)heightwidthr) param_name) super__init__rr#r$r%r&r'r(r)r*r+) selfr#r$r%r&r'r(r)r*r+kwargs __class__s r/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/mobilevit/image_processing_mobilevit.pyr9 MobileViTImageProcessor.__init___s "6"'tos-CTU;!*!6IsUX[TU]"U4SU0UD6$)z Preprocesses a batch of images and optionally segmentation maps. Overrides the `__call__` method of the `Preprocessor` class so that both images and segmentation maps can be passed in as positional arguments. segmentation_maps)r8__call__)r:imagesrQr;r<s r=rR MobileViTImageProcessor.__call__s wV:KVvVVr?c U(aURU5nU(aURXXS9nU(aURXU S9nU(aURXU S9nU(aUR XS9nU$)N)r@r$r%rB)r@scalerB)r@r$rB)rB)rNr rescale center_cropr ) r:r@r+r#r&r(r*r$r%r'r)rBs r= _preprocess#MobileViTImageProcessor._preprocesssv %%e,E KKeKoE LLuVgLhE $$5Te$fE ++E+WE r?c [U5nU(a%[U5(a[RS5 U c [ U5n UR USUUUUUUUU U S9 n[ XU S9nU$)zPreprocesses a single image.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.F) r@r+r#r$r%r&r'r(r)r*rB)input_channel_dim)rrlogger warning_oncerrYr ) r:r@r#r$r%r&r'r(r)r*rArBs r=_preprocess_image)MobileViTImageProcessor._preprocess_images u% /%00   s   $ >u E   "!))"7/!  ,ERcd r?segmentation_mapc D[U5nURS:XaSnUSn[RnOSnUc [ USS9nUR UUUU[ RSUUSUS9 nU(aURS5nUR[R5nU$) zPreprocesses a single mask.T)N.FrL) num_channels) r@r+r#r$r%r&r(r)r*rBr) rndimr FIRSTrrYrNEARESTsqueezeastypenpint64) r:rar+r#r$r(r)rBadded_channel_dims r=_preprocess_mask(MobileViTImageProcessor._preprocess_masks**:;  A % $ / :  0 6 6  %  ($BCSbc$d!++"-'//)"'/,   /77: +22288<r?rSrQreturn_tensorscUbUO URnUbUO URnUbUO URnUbUO URnUbUO URnU bU O UR n UbUO UR n[USS9nU bU O URn [U SS9n U bU O URn [U5nUb [USS9n[U5n[U5(d [S5eUb[U5(d [S5e[UUUU UUUS 9 UVs/sHnURUUUUUUUU U U US 9 PM nnS U0nUb*UVs/sHnURUU UUUU US 9PM nnUUS '[!UU S9$s snfs snf)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`. segmentation_maps (`ImageInput`, *optional*): Segmentation map 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 resizing. resample (`int`, *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_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image by rescale factor. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to rescale the image by if `do_rescale` 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 center crop if `do_center_crop` is set to `True`. do_flip_channel_order (`bool`, *optional*, defaults to `self.do_flip_channel_order`): Whether to flip the channel order of the image. do_reduce_labels (`bool`, *optional*, defaults to `self.do_reduce_labels`): Whether or not to reduce all label values of segmentation maps by 1. Usually used for datasets where 0 is used for background, and background itself is not included in all classes of a dataset (e.g. ADE20k). The background label will be replaced by 255. 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. 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. Fr0r)r5rc)expected_ndimszkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.zvInvalid segmentation map 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$r%r&r'r(r)r*rArBr")rar+r#r$r(r)rBlabels)data tensor_type)r#r%r&r'r(r*r$rr)r+rrrDrr_rmr)r:rSrQr#r$r%r&r'r(r)r*r+rorArBimgrsras r= preprocess"MobileViTImageProcessor.preprocessEs D"+!6IDNN '38#-#9Zt +9+E4K^K^+9+E4K^K^%:%F !DLfLf 'tTYYTU;!*!6IDNN !) D /?/K+QUQfQf)&1  ( 89J[\ ] )&1F##:   (>O1P1P:  &!)) 0   " "#!%--#&;'"3 #   "'  (): !):$%%%5%5'#1'&7&):  !/DN>BBG ( !s #E= F target_sizesc URnUb[U5[U5:wa [S5e[U5(aUR 5n/n[ [U55Han[ RRRX5RSS9X%SSS9nUSRSS9nURU5 Mc U$URSS9n[ URS5Vs/sHoUPM nnU$s snf)a Converts the output of [`MobileViTForSemanticSegmentation`] into semantic segmentation maps. Only supports PyTorch. Args: outputs ([`MobileViTForSemanticSegmentation`]): Raw outputs of the model. target_sizes (`list[Tuple]` of length `batch_size`, *optional*): List of tuples corresponding to the requested final size (height, width) of each prediction. If unset, predictions will not be resized. Returns: semantic_segmentation: `list[torch.Tensor]` of length `batch_size`, where each item is a semantic segmentation map of shape (height, width) corresponding to the target_sizes entry (if `target_sizes` is specified). Each entry of each `torch.Tensor` correspond to a semantic class id. zTMake sure that you pass in as many target sizes as the batch dimension of the logitsr)dimbilinearF)r$mode align_cornersrL)logitslenrDrnumpyrangetorchnn functional interpolate unsqueezeargmaxappendshape) r:outputsrxr~semantic_segmentationidxresized_logits semantic_mapis r="post_process_semantic_segmentation:MobileViTImageProcessor.post_process_semantic_segmentations""  #6{c,// j|,,+113 $& !S[)!&!4!4!@!@K))a)0|7Hzin"A" .a077A7> %,,\: *%$%+MMaM$8 !GLMbMhMhijMkGl$mGl!1%=Gl !$m$$%ns9D ) r)r(r*r+r&r#r%r'r$)NN)N)NNNNN) NNNNNNNNNN)NNNNNN)&__name__ __module__ __qualname____firstlineno____doc__model_input_namesrBILINEARboolrdictstrintrfloatr9rjndarrayr r r rrNrRrYr_rmrrfrPILImagervlisttupler__static_attributes__ __classcell__)r<s@r=r r 7s"H(()-'9'B'B,3#.2&*!&11tCH~&1% 1  1 c5j) 11DcN+1 $11 11D(:'B'B>BDH / zz/ 38n/ % / eC)9$9:; / $E#/?*?$@A /  / h?CDH gzzgeC)9$9:;g$E#/?*?$@A g  g(*W"*.15*..2DH      $tCH~&-.!DcN+$E#/?*?$@AD%))-15%)*.)-.204>BDH))D>)tCH~& ) -. ) TN )!)!)DcN+) (~)eC)9$9:;)$E#/?*?$@A) )\,0$()-)-.2DH& $& #4.& D> & tCH~& & ! & DcN+& $E#/?*?$@A&  & P%&37$()-15%)*.)-.204+/;?(8(>(>DHQCQC$J/QCD> QC tCH~& QC -. QCTNQC!QC!QCDcN+QC (~QC#4.QC!sJ!78QC&QC$E#/?*?$@AQC !QC'QCh)%QUV[Q\H])%)%r?r ))rtypingrrrrjimage_processing_utilsrrrimage_transformsr r r r image_utilsr rrrrrrrrutilsrrrrrrutils.import_utilsrrr get_loggerrr]r __all__r7r?r=rs+"UUuu   +   H % ;K%0K% K%\ % %r?