dj;J &dZddlZddlZddlmZmZddlmZddlmZ ddlm Z ddlm Z ddlm Z dd lm Z dd lmZdd lmZdd lmZdd lmZddlmZe j0Zej4Zej8Zej<ZGddej@Z!Gddej@Z"ejFdejHejJe"ejLejNZ(Gddej@Z)e jTdejJe)ejJejLfe jTdejLejLejJejVejJe"fe jTdejLejLejJejVejNejJe"fe jTdejLejLejJejVejNfe jTdejLejJe!fe jXdejJe"gde jTdejLfe jXdejLgdfZ-ej\GddZ/ej\Gdd Z0Gd!d"Z1y)#zMediaPipe image segmenter task.N)CallableOptional)async_result_dispatcher) base_options)base_options_c)mediapipe_c_bindings)mediapipe_c_utils)serial_dispatcher) doc_controls)image)image_processing_options)image_processing_options_c)vision_task_running_modecdeZdZdejej fdej fgZy) MpStringListCstrings num_stringsN)__name__ __module__ __qualname__ctypesPOINTERc_char_pc_int_fields_p/root/repos/pocs/video-evals/.venv/lib/python3.12/site-packages/mediapipe/tasks/python/vision/image_segmenter.pyrr&s,.&..12fll#(rrceZdZdejej fdej fdej fdej fdejejfdej fgZy)ImageSegmenterResultCconfidence_masksconfidence_masks_count category_maskhas_category_maskquality_scoresquality_scores_countN) rrrrrc_void_pc_uint32c_floatrrrrr r -sg>6>>&//:;1(FOO,78v/ (rr ceZdZdZdej fdejfdejfdejfdejfde fgZ e e jdej dededede ddf d Zy ) ImageSegmenterOptionsCz"C types for ImageSegmenterOptions.r running_modedisplay_names_localeoutput_confidence_masksoutput_category_maskresult_callbackreturnc\tjd}|||j||||S)z@Creates an ImageSegmenterOptionsC object from the given options.r)rr,r-r.r/r0)rrctype)clsrr,r.r/r0 empty_strings rfrom_c_optionsz%ImageSegmenterOptionsC.from_c_optionsKs7??3'L !!'') 71'  rN)rrr__doc__r BaseOptionsCrrrc_bool_C_TYPES_RESULT_CALLBACKr classmethodr do_not_generate_docs _RunningModeboolr6rrrr+r+@s*~223v||$v/ &--0v}}-23 ($$"//! $  !  0  %rr+MpImageSegmenterCreateMpImageSegmenterSegmentImageMpImageSegmenterSegmentForVideoMpImageSegmenterSegmentAsyncMpImageSegmenterGetLabelsMpImageSegmenterCloseResultMpImageSegmenterCloseMpStringListFreeceZdZUdZdZeeeje d<dZ eeje d<e e jdeddfdZy)ImageSegmenterResultaWOutput result of ImageSegmenter. confidence_masks: multiple masks of float image where, for each mask, each pixel represents the prediction confidence, usually in the [0, 1] range. category_mask: a category mask of uint8 image where each pixel represents the class which the pixel in the original image was predicted to belong to. Nr!r#c_resultr1cNd}d}|jdkDrLt|jDcgc].}tjj |j |0}}|j dkDr)tjj |j}|||Scc}w)zFCreates an `ImageSegmenterResult` object from the given ctypes struct.Nr)r!r#)r"range image_moduleImagecreate_from_ctypesr!r$r#)r4rIr!r#is r from_ctypesz ImageSegmenterResult.from_ctypess M''!+889    / /0I0I!0L M!!A%"((;;  m )# s3B")rrrr7r!rlistrLrM__annotations__r#r;r r<r rPrrrrHrHsi:>HT,"4"456=04-,,,-4$$*%rrHceZdZUdZeed<ejZeed<dZ e ed<dZ e ed<dZ e eeej"egdfed <y) ImageSegmenterOptionsa7Options for the image segmenter task. Attributes: base_options: Base options for the image segmenter task. running_mode: The running mode of the task. Default to the image mode. Image segmenter task has three running modes: 1) The image mode for segmenting objects on single image inputs. 2) The video mode for segmenting objects on the decoded frames of a video. 3) The live stream mode for segmenting objects on a live stream of input data, such as from camera. output_confidence_masks: Whether to output confidence masks. output_category_mask: Whether to output category mask. result_callback: The user-defined result callback for processing live stream data. The result callback should only be specified when the running mode is set to the live stream mode. rr,Tr.Fr/Nr0)rrrr7 _BaseOptionsrRr=IMAGEr,r.r>r/r0rrrHrLrMintrrrrTrTsf +11, 1"&4&$$ 8$l&8&8#>DE rrTc eZdZUdZej ed<ejed<e ed<e ed<dej dejde d e d d f d Z e d e d dfdZe ded dfdZ ddej$deed efdZ ddej$dedeed efdZ ddej$dedeed d fdZed ee fdZdZdZdZdZ y )ImageSegmenteraClass that performs image segmentation on images. The API expects a TFLite model with mandatory TFLite Model Metadata. Input tensor: (kTfLiteUInt8/kTfLiteFloat32) - image input of size `[batch x height x width x channels]`. - batch inference is not supported (`batch` is required to be 1). - RGB and greyscale inputs are supported (`channels` is required to be 1 or 3). - if type is kTfLiteFloat32, NormalizationOptions are required to be attached to the metadata for input normalization. Output tensors: (kTfLiteUInt8/kTfLiteFloat32) - list of segmented masks. - if `output_category_mask` is True, uint8 Image, Image vector of size 1. - if `output_confidence_masks` is True, float32 Image list of size `channels`. - batch is always 1 An example of such model can be found at: https://tfhub.dev/tensorflow/lite-model/deeplabv3/1/metadata/2 _lib_handle _dispatcher_async_callbacklibhandle dispatcherasync_callbackr1NcJ||_||_||_||_d|_y)a.Initializes the `ImageSegmenter` object. Args: lib: The dispatch library to use for the image segmenter. handle: The C pointer to the image segmenter. dispatcher: The async result handler for the image segmenter. async_callback: The c callback for the image segmenter. N)rZr[r\r]_labels)selfr^r_r`ras r__init__zImageSegmenter.__init__s)DIDL!D)DDLr model_pathcrt|}t|tj}|j |S)a[Creates an `ImageSegmenter` object from a TensorFlow Lite model and the default `ImageSegmenterOptions`. Note that the created `ImageSegmenter` instance is in image mode, for performing image segmentation on single image inputs. Args: model_path: Path to the model. Returns: `ImageSegmenter` object that's created from the model file and the default `ImageSegmenterOptions`. Raises: ValueError: If failed to create `ImageSegmenter` object from the provided file such as invalid file path. RuntimeError: If other types of error occurred. )model_asset_path)rr,)rUrTr=rVcreate_from_options)r4rfroptionss rcreate_from_model_pathz%ImageSegmenter.create_from_model_paths6& .convert_resultDs@ ah&228!?  !  rr r c||j}t}|r#tj|j nd}|j j |j||tj|tj|}|j jtj||S)aPerforms the actual segmentation task on the provided MediaPipe Image. Args: image: MediaPipe Image. image_processing_options: Options for image processing. Returns: If the output_type is CATEGORY_MASK, the returned vector of images is per-category segmented image mask. If the output_type is CONFIDENCE_MASK, the returned vector of images contains only one confidence image mask. A segmentation result object that contains a list of segmentation masks as images. Raises: ValueError: If any of the input arguments is invalid. RuntimeError: If image segmentation failed to run. N) _image_ptrr rr}r|rZr@r[rHrPrD)rdr r c_imagerI options_cresults rsegmentzImageSegmenter.segmentes,G$&H $  -779:   II**  X  " - -h 7FII))&,,x*@A Mrroc ~|j}t}|r#tj|j nd}|j j |j|||tj|tj|}|j jtj||S)aPerforms segmentation on the provided video frames. Only use this method when the ImageSegmenter is created with the video running mode. It's required to provide the video frame's timestamp (in milliseconds) along with the video frame. The input timestamps should be monotonically increasing for adjacent calls of this method. Args: image: MediaPipe Image. timestamp_ms: The timestamp of the input video frame in milliseconds. image_processing_options: Options for image processing. Returns: If the output_type is CATEGORY_MASK, the returned vector of images is per-category segmented image mask. If the output_type is CONFIDENCE_MASK, the returned vector of images contains only one confidence image mask. A segmentation result object that contains a list of segmentation masks as images. Raises: ValueError: If any of the input arguments is invalid. RuntimeError: If image segmentation failed to run. N) rr rr}r|rZrAr[rHrPrD)rdr ror rrIrrs rsegment_for_videoz ImageSegmenter.segment_for_videos:G$&H $  -779:   II--  X " - -h 7FII))&,,x*@A Mrc|j}|r#tj|jnd}|jj |j |||y)aSends live image data (an Image with a unique timestamp) to perform image segmentation. Only use this method when the ImageSegmenter is created with the live stream running mode. The input timestamps should be monotonically increasing for adjacent calls of this method. This method will return immediately after the input image is accepted. The results will be available via the `result_callback` provided in the `ImageSegmenterOptions`. The `segment_async` method is designed to process live stream data such as camera input. To lower the overall latency, image segmenter may drop the input images if needed. In other words, it's not guaranteed to have output per input image. The `result_callback` prvoides: - A segmentation result object that contains a list of segmentation masks as images. - The input image that the image segmenter runs on. - The input timestamp in milliseconds. Args: image: MediaPipe Image. timestamp_ms: The timestamp of the input image in milliseconds. image_processing_options: Options for image processing. Raises: ValueError: If the current input timestamp is smaller than what the image segmenter has already processed. N)rrr}r|rZrBr[)rdr ror rrs r segment_asynczImageSegmenter.segment_asyncsYBG $  -779:   II**  rc|jst}|jj|jt j |g|_t|jD]P}|j|}t j|jd}|jj|R|jjt j ||jS)a|Get the category label list the ImageSegmenter can recognize. For CATEGORY_MASK type, the index in the category mask corresponds to the category in the label list. For CONFIDENCE_MASK type, the output mask list at index corresponds to the category in the label list. If there is no label map provided in the model file, empty label list is returned. zutf-8)rcrrZrCr[rr}rKrr string_atdecodeappendrF)rdc_labelsrOc_labellabels rlabelszImageSegmenter.labelss <<h ii)) ,, ,,x dlX))*#!""1%  )009 E"# ii  h!78 <<rc|jsy|jj|jd|_|jj |jj y)zCloses ImageSegmenter.N)r[rZrEr\closerds rrzImageSegmenter.closesI << II##DLL1DLIIOOrc|S)z1Returns `self` upon entering the runtime context.rrs r __enter__zImageSegmenter.__enter__ s Krc$|jy)aCloses ImageSegmenters and exits the context manager. Args: exc_type: The exception type that caused the context manager to exit. exc_value: The exception value that caused the context manager to exit. traceback: The exception traceback that caused the context manager to exit. Raises: RuntimeError: If the MediaPipe Gesture Recognizer task failed to close. Nr)rdexc_type exc_value tracebacks r__exit__zImageSegmenter.__exit__s  JJLrc$|jyNrrs r__del__zImageSegmenter.__del__s JJLrr)!rrrr7r SerialDispatcherrRrr'rzr:rer;strrkrTrirLrMr_ImageProcessingOptionsrHrrWrrpropertyrQrrrrrrrrrYrYs0 *** ??%%++  - -oo)  /   *,c,6F,,06)666vEI%   %!))@ A% %VEI -   --!))@ A -  -fEI ,   ,,!))@ A ,  ,\ d3i 2 rrY)2r7r dataclassestypingrrmediapipe.tasks.python.corerrbase_options_modulerrr r 1mediapipe.tasks.python.core.optional_dependenciesr "mediapipe.tasks.python.vision.corer rLr image_processing_options_modulerrru BaseOptionsrUImageProcessingOptionsrVisionTaskRunningModer=AsyncResultDispatcherrz Structurerr CFUNCTYPEc_int32rr'c_int64r:r+CStatusFunctionImageProcessingOptionsC CFunctionrx dataclassrHrTrYrrrrs& %?K6<99JDjI^".. 9PP"88 0FFF$$F,,,6++ NNFNN() OO NN V--D&%% FNN1 2 FNN6?? + &%%& OO OO FNN5MM N FNN0 1  &%%) OO OO FNN5MM N NN FNN0 1   &%%& OO OO FNN5MM N NN  &%%# OO FNN= )  % - ./  &%%   OO  i;| """J    4@@r