djyE dZddlZddlZddlmZmZddlmZddlm Z ddl m Z ddl mZddl mZdd l mZdd l mZdd l mZdd l mZdd lmZddlmZddlmZddlmZddlmZ ejBZ"ejFZ$e jJZ&ejNZ(ejRZ*ejVZ,GddejZZ.GddejZZ/ej`dejbe/ejbejdfej`dejdejdejbejfejbe jhfej`dejdejdejbejfejjejbe jhfej`dejdejdejbejfejjfejldejbe jhgdej`dejdffZ7ejpdejrejbe jhejdejjZ:ejvGddZ<GddZ=y) zMediaPipe image embedder task.N)CallableOptional)embedding_result)embedding_result_ccosine_similarity)async_result_dispatcher) base_options)base_options_c)mediapipe_c_bindings)mediapipe_c_utils)serial_dispatcher) doc_controls)image)image_processing_options)image_processing_options_c)vision_task_running_modecHeZdZdZdej fdej fgZy)_EmbedderOptionsCzC struct for embedder options. l2_normalizequantizeN)__name__ __module__ __qualname____doc__ctypesc_bool_fields_o/root/repos/pocs/video-evals/.venv/lib/python3.12/site-packages/mediapipe/tasks/python/vision/image_embedder.pyrr+s&&v}}%6==!(r rc eZdZdZdej fdejfdefdejdejeje jejejfgZy)ImageEmbedderOptionsCz7The MediaPipe Tasks ImageEmbedderOptions CTypes struct.r running_modeembedder_optionsresult_callbackN)rrrrbase_options_c_module BaseOptionsCrc_intr CFUNCTYPEc_int32POINTERembedding_result_c_moduleEmbeddingResultCc_void_pc_int64rrr r!r#r#4sw?,99:v||$,-  &  nnfnn6GGHoonn    (r r#MpImageEmbedderCreateMpImageEmbedderEmbedImageMpImageEmbedderEmbedForVideoMpImageEmbedderEmbedAsyncMpImageEmbedderCloseResultMpImageEmbedderClosecVeZdZUdZeed<ejZeed<dZ e e ed<dZ e e ed<dZ e eeej"egdfed<dZe eej*ej,ej,ej.gdfed<ej2d ej6d efd Zy) ImageEmbedderOptionsaOptions for the image embedder task. Attributes: base_options: Base options for the image embedder task. running_mode: The running mode of the task. Default to the image mode. Image embedder task has three running modes: 1) The image mode for embedding image on single image inputs. 2) The video mode for embedding image on the decoded frames of a video. 3) The live stream mode for embedding image on a live stream of input data, such as from camera. l2_normalize: Whether to normalize the returned feature vector with L2 norm. Use this option only if the model does not already contain a native L2_NORMALIZATION TF Lite Op. In most cases, this is already the case and L2 norm is thus achieved through TF Lite inference. quantize: Whether the returned embedding should be quantized to bytes via scalar quantization. Embeddings are implicitly assumed to be unit-norm and therefore any dimension is guaranteed to have a value in [-1.0, 1.0]. Use the l2_normalize option if this is not the case. 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 r$Nrrr&_result_callback_c dispatcherreturnc|j|jt|_|jj }t |j|j}t||jj||jS)z*Generates an ImageEmbedderOptionsC object.)rr)r r$r%r&) wrap_callbackr&C_TYPES_RESULT_CALLBACKr9r to_ctypesrrrr#r$ctype)selfr:r embedder_options_cs r!r?zImageEmbedderOptions.to_ctypess )66 5D&&002N*&& !#&&,,+//  r )rrrr _BaseOptions__annotations__ _RunningModeIMAGEr$rrboolrr&rImageEmbedderResult image_moduleImageintr9rr+r/r0rdo_not_generate_docsr AsyncResultDispatcherr#r?rr r!r8r8s,+11, 1!%,%!(HTN! 8#\%7%7=tCD  hnnoooonn       $$/EE%r r8c eZdZUdZej ed<ejed<e jed<dej dejde jfdZ e d e d dfd Ze d ed dfd Z ddej$deed efdZ ddej$dedeed efdZ ddej$dedeed dfdZdZe dej8dej8d efdZdZdZ dZ!y) ImageEmbedderaClass that performs embedding extraction on images. The API expects a TFLite model with optional, but strongly recommended, TFLite Model Metadata. Input tensor: (kTfLiteUInt8/kTfLiteFloat32) - image input of size `[batch x height x width x channels]`. - batch inference is not supported (`batch` is required to be 1). - only RGB inputs are supported (`channels` is required to be 3). - if type is kTfLiteFloat32, NormalizationOptions are required to be attached to the metadata for input normalization. At least one output tensor with: (kTfLiteUInt8/kTfLiteFloat32) - `N` components corresponding to the `N` dimensions of the returned feature vector for this output layer. - Either 2 or 4 dimensions, i.e. `[1 x N]` or `[1 x 1 x 1 x N]`. _lib_handle _dispatcherlibhandler:c.||_||_||_y)zInitializes a new ImageEmbedder instance. Args: lib: The dispatcher to use for all C function calls. handle: The C pointer to the underlying image embedder. dispatcher: The handler for async results. N)rPrQrR)rArSrTr:s r!__init__zImageEmbedder.__init__sDIDL!Dr model_pathr;crt|}t|tj}|j |S)aGCreates an `ImageEmbedder` object from a TensorFlow Lite model and the default `ImageEmbedderOptions`. Note that the created `ImageEmbedder` instance is in image mode, for embedding image on single image inputs. Args: model_path: Path to the model. Returns: `ImageEmbedder` object that's created from the model file and the default `ImageEmbedderOptions`. Raises: ValueError: If failed to create `ImageEmbedder` object from the provided file such as invalid file path. RuntimeError: If other types of error occurred. )model_asset_path)r r$)rCr8rErFcreate_from_options)clsrWr optionss r!create_from_model_pathz$ImageEmbedder.create_from_model_paths6& .convert_resultsF"ah)99EEhOi##66yAh< 00r ) converter)r:)running_mode_modulevalidate_running_moder$r&r load_shared_library_CTYPES_SIGNATURESrr,r-r.r/rKtuplerHrIrJ_AsyncResultDispatcherr?r1byref)r[r\rSrjr:ctypes_optionsembedder_handles r!rZz!ImageEmbedder.create_from_optionss"--g55  2 23E FC1nn % 6 6 1?? 1  1 "L$6$6; < 1,(.AJ&&z2Noo'O ^$fll?&C sO ;;r Nrrc|j}tj}|r#tj|j nd}|j j|j||tj|tjj|}|j jtj||S)a Performs image embedding extraction on the provided MediaPipe Image. Extraction is performed on the region of interest specified by the `roi` argument if provided, or on the entire image otherwise. Args: image: MediaPipe Image. image_processing_options: Options for image processing. Returns: An embedding result object that contains a list of embeddings. Raises: ValueError: If any of the input arguments is invalid. RuntimeError: If image embedder failed to run. N) _image_ptrr-r.rrrr?rPr2rQrcrdrer5)rArrc_imagerg options_crhs r!embedzImageEmbedder.embed=s*G(99;H $  -779:   II''  X  (77CCHMIII((h)?@ r rac |j}tj}|r#tj|j nd}|j j|j|||tj|tjj|}|j jtj||S)ayPerforms image embedding extraction on the provided video frames. Extraction is performed on the region of interested specified by the `roi` argument if provided, or on the entire image otherwise. Only use this method when the ImageEmbedder 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: An embedding result object that contains a list of embeddings. Raises: ValueError: If any of the input arguments is invalid. RuntimeError: If image embedder failed to run. N) rvr-r.rrrr?rPr3rQrcrdrer5)rArrarrwrgrxrhs r!embed_for_videozImageEmbedder.embed_for_videocs8G(99;H $  -779:   II**  X (77CCHMIII((h)?@ r c|j}|r#tj|jnd}|jj |j |||y)aSends live image data to embedder. The results will be available via the "result_callback" provided in the ImageEmbedderOptions. Embedding extraction is performed on the region of interested specified by the `roi` argument if provided, or on the entire image otherwise. Only use this method when the ImageEmbedder 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 `ImageEmbedderOptions`. The `embed_async` method is designed to process live stream data such as camera input. To lower the overall latency, image embedder may drop the input images if needed. In other words, it's not guaranteed to have output per input image. The `result_callback` provides: - An embedding result object that contains a list of embeddings. - The input image that the image embedder 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 embedder has already processed. N)rvrrrr?rPr4rQ)rArrarrwrxs r! embed_asynczImageEmbedder.embed_asyncsYJG $  -779:   II''  r c|jsy|jj|jd|_|jj |jj y)zCloses the ImageEmbedder.N)rQrPr6rRcloserAs r!rzImageEmbedder.closesI << II""4<<0DLIIOOr uvc.tj||S)a=Utility function to compute cosine similarity between two embedding entries. May return an InvalidArgumentError if e.g. the feature vectors are of different types (quantized vs. float), have different sizes, or have an L2-norm of 0. Args: u: An embedding entry. v: An embedding entry. Returns: The cosine similarity for the two embeddings. Raises: ValueError: May return an error if e.g. the feature vectors are of different types (quantized vs. float), have different sizes, or have an L2-norm of 0. r)r[rrs r!rzImageEmbedder.cosine_similaritys0  . .q! 44r c|S)z1Returns `self` upon entering the runtime context.rrs r! __enter__zImageEmbedder.__enter__s Kr c*~~~|jy)zFShuts down the MediaPipe task instance on exit of the context manager.Nr)rAexc_type exc_value tracebacks r!__exit__zImageEmbedder.__exit__s)YJJLr c$|jyNrrs r!__del__zImageEmbedder.__del__s JJLr r)"rrrrrSerialDispatcherrDrr/r rMrV classmethodstrr]r8rZrIrJr_ImageProcessingOptionsrHryrKr{r}rrc Embeddingfloatrrrrrr r!rOrOs& *** ??&<<<"  - -"oo"*?? "",c,o,,02<(2<2<2rr dataclassestypingrr,mediapipe.tasks.python.components.containersrrcrr-'mediapipe.tasks.python.components.utilsrmediapipe.tasks.python.corer r base_options_moduler r'r r r1mediapipe.tasks.python.core.optional_dependenciesr"mediapipe.tasks.python.vision.corerrIrimage_processing_options_moduler!image_processing_options_c_modulerrlrdrH BaseOptionsrCVisionTaskRunningModerEImageProcessingOptionsrrMrqLiveStreamPacket_LiveStreamPacket Structurerr#CStatusFunctionr,r/ImageProcessingOptionsCr.r0 CFunctionror*r+r> dataclassr8rOrr r!rs% %dhE?KO<99JDjn^-==".. "88 9PP0FF+<<((F,,*&%% FNN0 1 FNN6?? + &%%# OO OO FNN1II  FNN4EE F   &%%& OO OO FNN1II  NN FNN4EE F  &%%# OO OO FNN1II  NN    $ 1BB CD  &%% _3j+&** NNFNN,==> OO NN  <<<~kkr