a yf@sXdZddlmZddlmZddlmZddlmZddl m Z m Z Gdd d eZ d S) a> SAM model interface. This module provides an interface to the Segment Anything Model (SAM) from Ultralytics, designed for real-time image segmentation tasks. The SAM model allows for promptable segmentation with unparalleled versatility in image analysis, and has been trained on the SA-1B dataset. It features zero-shot performance capabilities, enabling it to adapt to new image distributions and tasks without prior knowledge. Key Features: - Promptable segmentation - Real-time performance - Zero-shot transfer capabilities - Trained on SA-1B dataset )Path)Model) model_info) build_sam) Predictor SAM2PredictorcsfeZdZdZdddfdd Zdeddd Zdfd d Zdd dZdddZ e ddZ Z S)SAMa SAM (Segment Anything Model) interface class for real-time image segmentation tasks. This class provides an interface to the Segment Anything Model (SAM) from Ultralytics, designed for promptable segmentation with versatility in image analysis. It supports various prompts such as bounding boxes, points, or labels, and features zero-shot performance capabilities. Attributes: model (torch.nn.Module): The loaded SAM model. is_sam2 (bool): Indicates whether the model is SAM2 variant. task (str): The task type, set to "segment" for SAM models. Methods: predict: Performs segmentation prediction on the given image or video source. info: Logs information about the SAM model. Examples: >>> sam = SAM("sam_b.pt") >>> results = sam.predict("image.jpg", points=[[500, 375]]) >>> for r in results: >>> print(f"Detected {len(r.masks)} masks") sam_b.ptN)returncs>|rt|jdvrtddt|jv|_tj|dddS)a Initializes the SAM (Segment Anything Model) instance. Args: model (str): Path to the pre-trained SAM model file. File should have a .pt or .pth extension. Raises: NotImplementedError: If the model file extension is not .pt or .pth. Examples: >>> sam = SAM("sam_b.pt") >>> print(sam.is_sam2) >z.ptz.pthz8SAM prediction requires pre-trained *.pt or *.pth model.Zsam2segment)modeltaskN)rsuffixNotImplementedErrorstemis_sam2super__init__)selfr  __class__X/var/www/html/django/DPS/env/lib/python3.9/site-packages/ultralytics/models/sam/model.pyr2sz SAM.__init__)weightscCst||_dS)aK Loads the specified weights into the SAM model. This method initializes the SAM model with the provided weights file, setting up the model architecture and loading the pre-trained parameters. Args: weights (str): Path to the weights file. Should be a .pt or .pth file containing the model parameters. task (str | None): Task name. If provided, it specifies the particular task the model is being loaded for. Examples: >>> sam = SAM("sam_b.pt") >>> sam._load("path/to/custom_weights.pt") N)rr )rrrrrr_loadEsz SAM._loadFc  sDtddddd}i||}t|||d}tj||fd|i|S)a Performs segmentation prediction on the given image or video source. Args: source (str | PIL.Image | numpy.ndarray): Path to the image or video file, or a PIL.Image object, or a numpy.ndarray object. stream (bool): If True, enables real-time streaming. bboxes (List[List[float]] | None): List of bounding box coordinates for prompted segmentation. points (List[List[float]] | None): List of points for prompted segmentation. labels (List[int] | None): List of labels for prompted segmentation. **kwargs (Any): Additional keyword arguments for prediction. Returns: (List): The model predictions. Examples: >>> sam = SAM("sam_b.pt") >>> results = sam.predict("image.jpg", points=[[500, 375]]) >>> for r in results: ... print(f"Detected {len(r.masks)} masks") g?r predicti)confrmodeZimgsz)bboxespointslabelsprompts)dictrr) rsourcestreamrr r!kwargsZ overridesr"rrrrVs z SAM.predictcKs|j|||||fi|S)a Performs segmentation prediction on the given image or video source. This method is an alias for the 'predict' method, providing a convenient way to call the SAM model for segmentation tasks. Args: source (str | PIL.Image | numpy.ndarray | None): Path to the image or video file, or a PIL.Image object, or a numpy.ndarray object. stream (bool): If True, enables real-time streaming. bboxes (List[List[float]] | None): List of bounding box coordinates for prompted segmentation. points (List[List[float]] | None): List of points for prompted segmentation. labels (List[int] | None): List of labels for prompted segmentation. **kwargs (Any): Additional keyword arguments to be passed to the predict method. Returns: (List): The model predictions, typically containing segmentation masks and other relevant information. Examples: >>> sam = SAM("sam_b.pt") >>> results = sam("image.jpg", points=[[500, 375]]) >>> print(f"Detected {len(results[0].masks)} masks") )r)rr$r%rr r!r&rrr__call__qsz SAM.__call__TcCst|j||dS)a Logs information about the SAM model. This method provides details about the Segment Anything Model (SAM), including its architecture, parameters, and computational requirements. Args: detailed (bool): If True, displays detailed information about the model layers and operations. verbose (bool): If True, prints the information to the console. Returns: (Tuple): A tuple containing the model's information (string representations of the model). Examples: >>> sam = SAM("sam_b.pt") >>> info = sam.info() >>> print(info[0]) # Print summary information )detailedverbose)rr )rr(r)rrrinfoszSAM.infocCsdd|jrtntiiS)a Provides a mapping from the 'segment' task to its corresponding 'Predictor'. Returns: (Dict[str, Type[Predictor]]): A dictionary mapping the 'segment' task to its corresponding Predictor class. For SAM2 models, it maps to SAM2Predictor, otherwise to the standard Predictor. Examples: >>> sam = SAM("sam_b.pt") >>> task_map = sam.task_map >>> print(task_map) {'segment': } r Z predictor)rrr)rrrrtask_mapsz SAM.task_map)r )N)FNNN)NFNNN)FT) __name__ __module__ __qualname____doc__rstrrrr'r*propertyr+ __classcell__rrrrr s  r N) r/pathlibrZultralytics.engine.modelrZultralytics.utils.torch_utilsrbuildrrrrr rrrrs