djO dZddlZddlZddlmZmZmZmZddlm Z ddlm Z ddl mZddl mZddl mZdd l mZdd l mZdd l mZdd lmZdd lmZddlmZddlmZddlm Z!e jDZ#ejHZ%e!jLZ'ejPZ)ejTZ+ejXZ-ej\dej^ej`e jbejdejfZ4GddejjZ6ejndej`e6ej`ejdfejndejdejdej`ejpej`e jbfejndejdejdej`ejpejfej`e jbfejndejdejdej`ejpejffejrdej`e jbgdejndejdffZ:ejvGddZ<GddZ=y)zMediaPipe object detector task.N)CallableListOptionalTuple) detections) detections_c)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_modeceZdZdZdej fdejfdejfdejfdejfdejejfdejfd ejejfd ejfd e fg Z e ejdej dedeedeedeedeeed eeed e d dfd Zy)ObjectDetectorOptionsCz.The object detector options used in the C API.r running_modedisplay_names_locale max_resultsscore_thresholdcategory_allowlistcategory_allowlist_countcategory_denylistcategory_denylist_countresult_callbackreturnc tj|} tj|} |r t|nd} |r t|nd} |||j|||| | | | | S)z@Creates an ObjectDetectorOptionsC object from the given options.r) r rrrrrrrrr)mediapipe_c_bindings_c_moduleconvert_strings_to_ctypes_arraylenctype) clsr rrrrrrrcategory_allowlist_ccategory_denylist_ccategory_allowlist_count_ccategory_denylist_count_cs p/root/repos/pocs/video-evals/.venv/lib/python3.12/site-packages/mediapipe/tasks/python/vision/object_detector.pyfrom_c_optionsz%ObjectDetectorOptionsC.from_c_optionsCs &EE   &EE  $6 1#4  !!''1'/!;- 9'  N)__name__ __module__ __qualname____doc__base_options_c_module BaseOptionsCctypesc_intc_char_pc_floatPOINTER_C_TYPES_RESULT_CALLBACK_fields_ classmethodrdo_not_generate_docs _RunningModerstrintfloatrr+r,r*rr3s:6,99:v||$v/fll#&..)^V^^FOO<=!6<<0NFNN6??;< &,,/23 ($$))66)!)%SM ) C= )   )#49-)"$s),)0) )%)r,rMpObjectDetectorCreateMpObjectDetectorDetectImageMpObjectDetectorDetectForVideoMpObjectDetectorDetectAsyncMpObjectDetectorCloseResultMpObjectDetectorCloseceZdZUdZeed<ejZeed<dZ e e ed<dZ e e ed<dZe eed <dZe ee ed <dZe ee ed <dZe eej,ej0e gdfed <y) ObjectDetectorOptionsaOptions for the object detector task. Attributes: base_options: Base options for the object detector task. running_mode: The running mode of the task. Default to the image mode. Object detector task has three running modes: 1) The image mode for detecting objects on single image inputs. 2) The video mode for detecting objects on the decoded frames of a video. 3) The live stream mode for detecting objects on a live stream of input data, such as from camera. display_names_locale: The locale to use for display names specified through the TFLite Model Metadata. max_results: The maximum number of top-scored classification results to return. score_threshold: Overrides the ones provided in the model metadata. Results below this value are rejected. category_allowlist: Allowlist of category names. If non-empty, detection results whose category name is not in this set will be filtered out. Duplicate or unknown category names are ignored. Mutually exclusive with `category_denylist`. category_denylist: Denylist of category names. If non-empty, detection results whose category name is in this set will be filtered out. Duplicate or unknown category names are ignored. Mutually exclusive with `category_allowlist`. result_callback: The user-defined result callback for processing live stream data. The result callback should only be specified when the running mode is set to the live stream mode. r rNrrgrrrr)r-r.r/r0 _BaseOptions__annotations__r<IMAGErrrr=rr>rr?rrrrrdetections_moduleDetectionResult image_moduleImager@r,r*rHrHs8+11, 1(, ,!+x}!%(/8E?(,0htCy)0+/Xd3i(/  8  , ,l.@.@# F L r,rHc eZdZUdZej ed<ejed<e ed<e ed<dej dejde d e fd Z e d e d dfd Ze ded dfdZ ddej$deed efdZ ddej$dedeed efdZ ddej$dedeed dfdZdZdZdZdZy)ObjectDetectoraClass that performs object detection 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). - only RGB inputs are supported (`channels` is required to be 3). - if type is kTfLiteFloat32, NormalizationOptions are required to be attached to the metadata for input normalization. Output tensors must be the 4 outputs of a `DetectionPostProcess` op, i.e: (kTfLiteFloat32) - locations tensor of size `[num_results x 4]`, the inner array representing bounding boxes in the form [top, left, right, bottom]. - BoundingBoxProperties are required to be attached to the metadata and must specify type=BOUNDARIES and coordinate_type=RATIO. (kTfLiteFloat32) - classes tensor of size `[num_results]`, each value representing the integer index of a class. - optional (but recommended) label map(s) can be attached as AssociatedFile-s with type TENSOR_VALUE_LABELS, containing one label per line. The first such AssociatedFile (if any) is used to fill the `class_name` field of the results. The `display_name` field is filled from the AssociatedFile (if any) whose locale matches the `display_names_locale` field of the `ObjectDetectorOptions` used at creation time ("en" by default, i.e. English). If none of these are available, only the `index` field of the results will be filled. (kTfLiteFloat32) - scores tensor of size `[num_results]`, each value representing the score of the detected object. - optional score calibration can be attached using ScoreCalibrationOptions and an AssociatedFile with type TENSOR_AXIS_SCORE_CALIBRATION. See metadata_schema.fbs [1] for more details. (kTfLiteFloat32) - integer num_results as a tensor of size `[1]` An example of such model can be found at: https://tfhub.dev/google/lite-model/object_detection/mobile_object_localizer_v1/1/metadata/1 [1]: https://github.com/google/mediapipe/blob/6cdc6443b6a7ed662744e2a2ce2d58d9c83e6d6f/mediapipe/tasks/metadata/metadata_schema.fbs#L456 _lib_handle _dispatcher_async_callbacklibhandle dispatcherasync_callbackc<||_||_||_||_y)a&Initializes the object detector. Args: lib: The dispatch library to use for the object detector. handle: The C pointer to the object detector. dispatcher: The async result handler for the object detector. async_callback: The c callback for the object detector. N)rSrTrUrV)selfrWrXrYrZs r*__init__zObjectDetector.__init__s"DIDL!D)Dr, model_pathrcrt|}t|tj}|j |S)aOCreates an `ObjectDetector` object from a TensorFlow Lite model and the default `ObjectDetectorOptions`. Note that the created `ObjectDetector` instance is in image mode, for detecting objects on single image inputs. Args: model_path: Path to the model. Returns: `ObjectDetector` object that's created from the model file and the default `ObjectDetectorOptions`. Raises: ValueError: If failed to create `ObjectDetector` object from the provided file such as invalid file path. RuntimeError: If other types of error occurred. )model_asset_path)r r)rJrHr<rLcreate_from_options)r%r^r optionss r*create_from_model_pathz%ObjectDetector.create_from_model_paths6& .convert_resultJs@ ah&228rrirOrP_AsyncResultDispatcher wrap_callbackr8rr+r to_ctypesrrrrrrAbyrefrR)r%rbrWrorY c_callbackctypes_optionsdetector_handles r*raz"ObjectDetector.create_from_options2s_$--g55 ( ; ;rrrrrrr@r,r*rRrRsp*X *** ??%%++*  - -*oo*) * / *(,c,6F,,0;);;;BEI*   *!))@ A* *`EI .   ..!))@ A .  .hEI 0   00!))@ A 0  0d r,rR)>r0r3 dataclassestypingrrrr,mediapipe.tasks.python.components.containersrrMrrumediapipe.tasks.python.corer r base_options_moduler r1r r!r r1mediapipe.tasks.python.core.optional_dependenciesr"mediapipe.tasks.python.vision.corerrOrimage_processing_options_moduler!image_processing_options_c_modulerrqrNri BaseOptionsrJVisionTaskRunningModer<ImageProcessingOptionsrAsyncResultDispatcherrxLiveStreamPacket_LiveStreamPacket CFUNCTYPEc_int32r7rvrwc_int64r8 StructurerCStatusFunctionImageProcessingOptionsC CFunctionrt dataclassrHrRr@r,r*rs& 22X\?KO]99JDjn^(88".. "88 9PP0FF+<<,6++ NNFNN&778 OO NN ;V--;~&%% FNN1 2 FNN6?? + &%%% OO OO FNN1II  FNN.?? @   &%%( OO OO FNN1II  NN FNN.?? @  &%%% OO OO FNN1II  NN    % +<< =>  &%% _3l ( ( ( VGGr,