cCiYSrSSKJr SSKJrJr SSKrSSKJ r SSK J r SSK J r SS KJrJrJr SS KJr \R("\5r\"5(aSSKr\"S S 9"S S\ 55rS/rg)z Processor class for SAM2. )deepcopy)OptionalUnionN) ImageInput)ProcessorMixin) BatchEncoding) TensorTypeis_torch_availablelogging)requires)torch)backendscB^\rSrSrSrS/rSrS"S\\S\4U4Sjjjr S#S\\ S \\ S \\ \ \ \ \ \ \R4S \\ \ \ \ \\R4S \\ \ \ \ \ \R4S \\ \ \ \ \R4S\\ \\4S\4SjjrS$S\SSSS4SjjrS%SjrS&SjrS'SjrSrSrS&S\ \R\R6\ 4S\S\S\S\\S\ 4 SjjrS(SjrS)S jrS!rU=r $)* Sam2Processor%a Constructs a SAM2 processor which wraps a SAM2 image processor and an 2D points & Bounding boxes processor into a single processor. [`Sam2Processor`] offers all the functionalities of [`Sam2ImageProcessorFast`] and [`Sam2VideoProcessor`]. See the docstring of [`~Sam2ImageProcessorFast.__call__`] and [`~Sam2VideoProcessor.__call__`] for more information. Args: image_processor (`Sam2ImageProcessorFast`): An instance of [`Sam2ImageProcessorFast`]. target_size (`int`, *optional*): The target size (target_size, target_size) to which the image will be resized. point_pad_value (`int`, *optional*, defaults to -10): The value used for padding input points. image_processorSam2ImageProcessorFast target_sizepoint_pad_valuec >[TU]"U40UD6 X0lUbX lgURRSUlg)Nheight)super__init__rrsizer)selfrrrkwargs __class__s b/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/sam2/processing_sam2.pyrSam2Processor.__init__:s? 3F3.*5*A;tG[G[G`G`aiGjimagessegmentation_maps input_points input_labels input_boxesoriginal_sizesreturn_tensorsreturnc ^UbUR"U4UUS.UD6n OXUbJ[U[R5(aUR 5R 5n[ SU0US9n O [S5eU SnUb2[U5S:wa#[U5[U5:wa [S5eUcUcUGbURUSS S S S 9n URUS SSS9n URUS SSSS 9n U bURU 5SS n U bURU 5SS nU bURU 5SS mU bU bW W:wa [S5eU b4[U 5S :a%[U4SjU 55(a [S5eU b]URU W S /-5n[R"U[RS9nURUUSS9 U R!SU05 U bHURU W5n[R"U[R"S9nU R!SU05 U bG[R"U [RS9nURUUSS9 U R!SU05 U $)a  This method uses [`Sam2ImageProcessorFast.__call__`] method to prepare image(s) for the model. It also prepares 2D points and bounding boxes for the model if they are provided. Args: images (`ImageInput`, *optional*): The image(s) to process. segmentation_maps (`ImageInput`, *optional*): The segmentation maps to process. input_points (`list[list[list[list[float]]]]`, `torch.Tensor`, *optional*): The points to add to the frame. input_labels (`list[list[list[int]]]`, `torch.Tensor`, *optional*): The labels for the points. input_boxes (`list[list[list[float]]]`, `torch.Tensor`, *optional*): The bounding boxes to add to the frame. original_sizes (`list[list[float]]`, `torch.Tensor`, *optional*): The original sizes of the images. return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. **kwargs: Additional keyword arguments to pass to the image processor. Returns: A [`BatchEncoding`] with the following fields: - `pixel_values` (`torch.Tensor`): The processed image(s). - `original_sizes` (`list[list[float]]`): The original sizes of the images. - `reshaped_input_sizes` (`torch.Tensor`): The reshaped input sizes of the images. - `labels` (`torch.Tensor`): The processed segmentation maps (if provided). - `input_points` (`torch.Tensor`): The processed points. - `input_labels` (`torch.Tensor`): The processed labels. - `input_boxes` (`torch.Tensor`): The processed bounding boxes. N)r#r(r') tensor_typez0Either images or original_sizes must be providedz{original_sizes must be of length 1 or len(images). If you are passing a single image, you must pass a single original_size.pointsz;[image level, object level, point level, point coordinates])expected_depth input_nameexpected_formatexpected_coord_sizerlabelsz([image level, object level, point level])r0r1r2boxesz)[image level, box level, box coordinates]zbInput points and labels have inconsistent dimensions. Please ensure they have the same dimensions.c3F># UHn[U5TS:v M g7f)r,N)len).0 img_boxesboxes_max_dimss r )Sam2Processor.__call__..s[?is9~q(99?s!zInput boxes have inconsistent dimensions that would require padding, but boxes cannot be padded due to model limitations. Please ensure all images have the same number of boxes.)dtypeT)preserve_paddingr$r%is_bounding_boxr&)r isinstancerTensorcputolistr ValueErrorr7_validate_single_input_get_nested_dimensionsany_pad_nested_listtensorfloat32_normalize_tensor_coordinatesupdateint64)rr"r#r$r%r&r'r(rencoding_image_processorprocessed_pointsprocessed_labelsprocessed_boxespoints_max_dimslabels_max_dims padded_points final_points padded_labels final_labels final_boxesr:s @r__call__Sam2Processor.__call__?sV  '+';';("3-( ( $  '.%,,77!/!3!3!5!'46F5Wes't $OP P22BC  #n"5":s>?RVYZ`Va?aN   #|'?;CZ#:: # ]$% ;   $:: # J ;   #99 " K$% :O +"&"="=>N"OPRQR"S+"&"="=>N"OPRQR"S*!%!>}X""k@R#S@R1HX$6@R#ST 3{+a/ /3{+,knd33%)%:%:;>;hiXikt%uKN-$c $Ts FFc[U5S:Xa U/US-$[US5Vs/sHo0RUSSU5PM sn$s snf)z Create an empty nested structure with given dimensions filled with pad_value. Args: dims (`list`): The dimensions of the nested structure. pad_value (`int`): The value to fill the structure with. r,rN)r7rr)rdimsrrs rr,Sam2Processor._create_empty_nested_structurejsX t9>;a( (V[\`ab\cVdeVdQR77QR)LVde eesA c[U[5(a'[U5S:XagSURUS5-$[U[R [ R45(a[UR5$g)zz Get the nesting level of a list structure. Args: input_list (`list`): The list to get the nesting level of. rr,) rArnr7_get_nesting_levelrlrmrrBri)r input_lists rr Sam2Processor._get_nesting_levelysh j$ ' ':!#t..z!}== =  RZZ$> ? ?z''( (r!rqr0r1r2r3c Ucg[U[R[R45(a{UR U:wa"[ SUSUSUSUR S3 5eUb5URSU:wa"[ SUSUSURSS 35eURX5$[U[5(a?URU5nXb:wa[ SUS US USUS 3 5eURX5$g) ae Validate a single input by ensuring proper nesting and raising an error if the input is not valid. Args: data (`torch.Tensor`, `np.ndarray`, or `list`): Input data to process. expected_depth (`int`): Expected nesting depth. input_name (`str`): Name of the input for error messages. expected_format (`str`): The expected format of the input. expected_coord_size (`int`, *optional*): Expected coordinate size (2 for points, 4 for boxes, None for labels). . NzInput z must be a tensor/array with z, dimensions. The expected nesting format is z. Got z dimensions.r^z as the last dimension, got .z must be a nested list with z( levels. The expected nesting format is z levels.) rArrBrlrmndimrErirkrnr)rrqr0r1r2r3rrs rrF$Sam2Processor._validate_single_inputs0 < dU\\2::6 7 7yyN* ZL(EnEUVBCRBSSYZ^ZcZcYddpq%0::b>%88$  ,IJ]I^^z{|F|FGI|J{KKLM//E E dD ! ! 33D9M. ZL(D^DTT|~M}NNTUbTcckl//E E "r!cU(aXR:gnURSSS9n[[U55HnXqRS:dMU[U5:aX'OUSnUR UR XXS9n U(a4WUn [R"U RX5XU5X'MXU'M g)a Helper method to normalize coordinates in a tensor across multiple images. Args: tensor (`torch.Tensor`): Input tensor with coordinates. original_sizes (`list`): Original image sizes. is_bounding_box (`bool`, *optional*, defaults to `False`): Whether coordinates are bounding boxes. preserve_padding (`bool`, *optional*, defaults to `False`): Whether to preserve padding values (for points). r^T)r}keepdimrr?N) rallrr7rirfrrwhere expand_as) rrJr'r@r>mask coord_maskimg_idxranormalized_coordsimg_masks rrL+Sam2Processor._normalize_tensor_coordinatess 111Db$7JS01Ga(;BSEX;X 7^lmn^o $($?$?$$fo}%@%!$)'2H&+kk **6?;=NW^P_'FO'87O2r!c HURR"UUUUUUU40UD6$)a Remove padding and upscale masks to the original image size. Args: masks (`Union[List[torch.Tensor], List[np.ndarray]]`): Batched masks from the mask_decoder in (batch_size, num_channels, height, width) format. original_sizes (`Union[torch.Tensor, List[Tuple[int,int]]]`): The original sizes of each image before it was resized to the model's expected input shape, in (height, width) format. mask_threshold (`float`, *optional*, defaults to 0.0): Threshold for binarization and post-processing operations. binarize (`bool`, *optional*, defaults to `True`): Whether to binarize the masks. max_hole_area (`float`, *optional*, defaults to 0.0): The maximum area of a hole to fill. max_sprinkle_area (`float`, *optional*, defaults to 0.0): The maximum area of a sprinkle to fill. apply_non_overlapping_constraints (`bool`, *optional*, defaults to `False`): Whether to apply non-overlapping constraints to the masks. Returns: (`torch.Tensor`): Batched masks in batch_size, num_channels, height, width) format, where (height, width) is given by original_size. )rpost_process_masks) rmasksr'mask_thresholdbinarize max_hole_areamax_sprinkle_area!apply_non_overlapping_constraintsrs rr Sam2Processor.post_process_maskss=F##66       -    r!)rr)Ni)NNNNNNN)F)r)N)rN)FF)TrrF)!__name__ __module__ __qualname____firstlineno____doc__ attributesimage_processor_classrrorrrrnr_rrBstrr r rZrfrkrGrIrrrlrmrFrLr__static_attributes__ __classcell__)rs@rrr%s $$J4kXc]k\_kk(,26UYMQNRKO;?B($B($J/B(uT$tDK/@*A%BELL%PQR B( uT$tCy/%:ELL%HIJ B( eDd5k):$;U\\$IJK B(!tDK'8%,,'F!GHB(!sJ!78B( B(JX](6 <$EL#J<| f..2 0FELL"**d230F0F 0F  0F &c] 0F 0Fd!8N*/, , r!r)rcopyrtypingrrrjrl image_utilsrprocessing_utilsrtokenization_utils_baser utilsr r r utils.import_utilsr get_loggerrloggerrr__all__r!rrss"%.4<<*   H % :e Ne e P  r!