Reference for ultralytics/models/sam/predict.py

def generate(
    self,
    im,
    crop_n_layers=0,
    crop_overlap_ratio=512 / 1500,
    crop_downscale_factor=1,
    point_grids=None,
    points_stride=32,
    points_batch_size=64,
    conf_thres=0.88,
    stability_score_thresh=0.95,
    stability_score_offset=0.95,
    crop_nms_thresh=0.7,
):
    """
    Perform image segmentation using the Segment Anything Model (SAM).

    This method segments an entire image into constituent parts by leveraging SAM's advanced architecture
    and real-time performance capabilities. It can optionally work on image crops for finer segmentation.

    Args:
        im (torch.Tensor): Input tensor representing the preprocessed image with shape (N, C, H, W).
        crop_n_layers (int): Number of layers for additional mask predictions on image crops.
        crop_overlap_ratio (float): Overlap between crops, scaled down in subsequent layers.
        crop_downscale_factor (int): Scaling factor for sampled points-per-side in each layer.
        point_grids (List[np.ndarray] | None): Custom grids for point sampling normalized to [0,1].
        points_stride (int): Number of points to sample along each side of the image.
        points_batch_size (int): Batch size for the number of points processed simultaneously.
        conf_thres (float): Confidence threshold [0,1] for filtering based on mask quality prediction.
        stability_score_thresh (float): Stability threshold [0,1] for mask filtering based on stability.
        stability_score_offset (float): Offset value for calculating stability score.
        crop_nms_thresh (float): IoU cutoff for NMS to remove duplicate masks between crops.

    Returns:
        pred_masks (torch.Tensor): Segmented masks with shape (N, H, W).
        pred_scores (torch.Tensor): Confidence scores for each mask with shape (N,).
        pred_bboxes (torch.Tensor): Bounding boxes for each mask with shape (N, 4).

    Examples:
        >>> predictor = Predictor()
        >>> im = torch.rand(1, 3, 1024, 1024)  # Example input image
        >>> masks, scores, boxes = predictor.generate(im)
    """
    import torchvision  # scope for faster 'import ultralytics'

    self.segment_all = True
    ih, iw = im.shape[2:]
    crop_regions, layer_idxs = generate_crop_boxes((ih, iw), crop_n_layers, crop_overlap_ratio)
    if point_grids is None:
        point_grids = build_all_layer_point_grids(points_stride, crop_n_layers, crop_downscale_factor)
    pred_masks, pred_scores, pred_bboxes, region_areas = [], [], [], []
    for crop_region, layer_idx in zip(crop_regions, layer_idxs):
        x1, y1, x2, y2 = crop_region
        w, h = x2 - x1, y2 - y1
        area = torch.tensor(w * h, device=im.device)
        points_scale = np.array([[w, h]])  # w, h
        # Crop image and interpolate to input size
        crop_im = F.interpolate(im[..., y1:y2, x1:x2], (ih, iw), mode="bilinear", align_corners=False)
        # (num_points, 2)
        points_for_image = point_grids[layer_idx] * points_scale
        crop_masks, crop_scores, crop_bboxes = [], [], []
        for (points,) in batch_iterator(points_batch_size, points_for_image):
            pred_mask, pred_score = self.prompt_inference(crop_im, points=points, multimask_output=True)
            # Interpolate predicted masks to input size
            pred_mask = F.interpolate(pred_mask[None], (h, w), mode="bilinear", align_corners=False)[0]
            idx = pred_score > conf_thres
            pred_mask, pred_score = pred_mask[idx], pred_score[idx]

            stability_score = calculate_stability_score(
                pred_mask, self.model.mask_threshold, stability_score_offset
            )
            idx = stability_score > stability_score_thresh
            pred_mask, pred_score = pred_mask[idx], pred_score[idx]
            # Bool type is much more memory-efficient.
            pred_mask = pred_mask > self.model.mask_threshold
            # (N, 4)
            pred_bbox = batched_mask_to_box(pred_mask).float()
            keep_mask = ~is_box_near_crop_edge(pred_bbox, crop_region, [0, 0, iw, ih])
            if not torch.all(keep_mask):
                pred_bbox, pred_mask, pred_score = pred_bbox[keep_mask], pred_mask[keep_mask], pred_score[keep_mask]

            crop_masks.append(pred_mask)
            crop_bboxes.append(pred_bbox)
            crop_scores.append(pred_score)

        # Do nms within this crop
        crop_masks = torch.cat(crop_masks)
        crop_bboxes = torch.cat(crop_bboxes)
        crop_scores = torch.cat(crop_scores)
        keep = torchvision.ops.nms(crop_bboxes, crop_scores, self.args.iou)  # NMS
        crop_bboxes = uncrop_boxes_xyxy(crop_bboxes[keep], crop_region)
        crop_masks = uncrop_masks(crop_masks[keep], crop_region, ih, iw)
        crop_scores = crop_scores[keep]

        pred_masks.append(crop_masks)
        pred_bboxes.append(crop_bboxes)
        pred_scores.append(crop_scores)
        region_areas.append(area.expand(len(crop_masks)))

    pred_masks = torch.cat(pred_masks)
    pred_bboxes = torch.cat(pred_bboxes)
    pred_scores = torch.cat(pred_scores)
    region_areas = torch.cat(region_areas)

    # Remove duplicate masks between crops
    if len(crop_regions) > 1:
        scores = 1 / region_areas
        keep = torchvision.ops.nms(pred_bboxes, scores, crop_nms_thresh)
        pred_masks, pred_bboxes, pred_scores = pred_masks[keep], pred_bboxes[keep], pred_scores[keep]

    return pred_masks, pred_scores, pred_bboxes

def get_im_features(self, im):
    """Extract image features using the SAM model's image encoder for subsequent mask prediction."""
    assert isinstance(self.imgsz, (tuple, list)) and self.imgsz[0] == self.imgsz[1], (
        f"SAM models only support square image size, but got {self.imgsz}."
    )
    self.model.set_imgsz(self.imgsz)
    return self.model.image_encoder(im)

def get_model(self):
    """Retrieve or build the Segment Anything Model (SAM) for image segmentation tasks."""
    from .build import build_sam  # slow import

    return build_sam(self.args.model)

def inference(self, im, bboxes=None, points=None, labels=None, masks=None, multimask_output=False, *args, **kwargs):
    """
    Perform image segmentation inference based on the given input cues, using the currently loaded image.

    This method leverages SAM's (Segment Anything Model) architecture consisting of image encoder, prompt
    encoder, and mask decoder for real-time and promptable segmentation tasks.

    Args:
        im (torch.Tensor): The preprocessed input image in tensor format, with shape (N, C, H, W).
        bboxes (np.ndarray | List | None): Bounding boxes with shape (N, 4), in XYXY format.
        points (np.ndarray | List | None): Points indicating object locations with shape (N, 2), in pixels.
        labels (np.ndarray | List | None): Labels for point prompts, shape (N,). 1 = foreground, 0 = background.
        masks (np.ndarray | None): Low-resolution masks from previous predictions, shape (N, H, W). For SAM H=W=256.
        multimask_output (bool): Flag to return multiple masks. Helpful for ambiguous prompts.
        *args (Any): Additional positional arguments.
        **kwargs (Any): Additional keyword arguments.

    Returns:
        pred_masks (torch.Tensor): The output masks in shape (C, H, W), where C is the number of generated masks.
        pred_scores (torch.Tensor): An array of length C containing quality scores predicted by the model for each mask.

    Examples:
        >>> predictor = Predictor()
        >>> predictor.setup_model(model_path="sam_model.pt")
        >>> predictor.set_image("image.jpg")
        >>> results = predictor(bboxes=[[0, 0, 100, 100]])
    """
    # Override prompts if any stored in self.prompts
    bboxes = self.prompts.pop("bboxes", bboxes)
    points = self.prompts.pop("points", points)
    masks = self.prompts.pop("masks", masks)
    labels = self.prompts.pop("labels", labels)

    if all(i is None for i in [bboxes, points, masks]):
        return self.generate(im, *args, **kwargs)

    return self.prompt_inference(im, bboxes, points, labels, masks, multimask_output)

@smart_inference_mode()
def inference_features(
    self,
    features,
    src_shape,
    dst_shape=None,
    bboxes=None,
    points=None,
    labels=None,
    masks=None,
    multimask_output=False,
):
    """
    Perform prompts preprocessing and inference on provided image features using the SAM model.

    Args:
        features (torch.Tensor | Dict[str, Any]): Extracted image features from the SAM/SAM2 model image encoder.
        src_shape (Tuple[int, int]): The source shape (height, width) of the input image.
        dst_shape (Tuple[int, int] | None): The target shape (height, width) for the prompts. If None, defaults to (imgsz, imgsz).
        bboxes (np.ndarray | List[List[float]] | None): Bounding boxes in xyxy format with shape (N, 4).
        points (np.ndarray | List[List[float]] | None): Points indicating object locations with shape (N, 2), in pixels.
        labels (np.ndarray | List[int] | None): Point prompt labels with shape (N, ).
        masks (List[np.ndarray] | np.ndarray | None): Masks for the objects, where each mask is a 2D array.
        multimask_output (bool): Flag to return multiple masks for ambiguous prompts.

    Returns:
        pred_masks (torch.Tensor): The output masks in shape (C, H, W), where C is the number of generated masks.
        pred_bboxes (torch.Tensor): Bounding boxes for each mask with shape (N, 6), where N is the number of boxes.
            Each box is in xyxy format with additional columns for score and class.

    Notes:
        - The input features is a torch.Tensor of shape (B, C, H, W) if performing on SAM, or a Dict[str, Any] if performing on SAM2.
    """
    dst_shape = dst_shape or (self.args.imgsz, self.args.imgsz)
    prompts = self._prepare_prompts(dst_shape, src_shape, bboxes, points, labels, masks)
    pred_masks, pred_scores = self._inference_features(features, *prompts, multimask_output)
    if len(pred_masks) == 0:
        pred_masks, pred_bboxes = None, torch.zeros((0, 6), device=pred_masks.device)
    else:
        pred_masks = ops.scale_masks(pred_masks[None].float(), src_shape, padding=False)[0]
        pred_masks = pred_masks > self.model.mask_threshold  # to bool
        pred_bboxes = batched_mask_to_box(pred_masks)
        # NOTE: SAM models do not return cls info. This `cls` here is just a placeholder for consistency.
        cls = torch.arange(len(pred_masks), dtype=torch.int32, device=pred_masks.device)
        pred_bboxes = torch.cat([pred_bboxes, pred_scores[:, None], cls[:, None]], dim=-1)
    return pred_masks, pred_bboxes

def postprocess(self, preds, img, orig_imgs):
    """
    Post-process SAM's inference outputs to generate object detection masks and bounding boxes.

    This method scales masks and boxes to the original image size and applies a threshold to the mask
    predictions. It leverages SAM's advanced architecture for real-time, promptable segmentation tasks.

    Args:
        preds (tuple): The output from SAM model inference, containing:
            - pred_masks (torch.Tensor): Predicted masks with shape (N, 1, H, W).
            - pred_scores (torch.Tensor): Confidence scores for each mask with shape (N, 1).
            - pred_bboxes (torch.Tensor, optional): Predicted bounding boxes if segment_all is True.
        img (torch.Tensor): The processed input image tensor with shape (C, H, W).
        orig_imgs (List[np.ndarray] | torch.Tensor): The original, unprocessed images.

    Returns:
        (List[Results]): List of Results objects containing detection masks, bounding boxes, and other
            metadata for each processed image.

    Examples:
        >>> predictor = Predictor()
        >>> preds = predictor.inference(img)
        >>> results = predictor.postprocess(preds, img, orig_imgs)
    """
    # (N, 1, H, W), (N, 1)
    pred_masks, pred_scores = preds[:2]
    pred_bboxes = preds[2] if self.segment_all else None
    names = dict(enumerate(str(i) for i in range(len(pred_masks))))

    if not isinstance(orig_imgs, list):  # input images are a torch.Tensor, not a list
        orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)

    results = []
    for masks, orig_img, img_path in zip([pred_masks], orig_imgs, self.batch[0]):
        if len(masks) == 0:
            masks, pred_bboxes = None, torch.zeros((0, 6), device=pred_masks.device)
        else:
            masks = ops.scale_masks(masks[None].float(), orig_img.shape[:2], padding=False)[0]
            masks = masks > self.model.mask_threshold  # to bool
            if pred_bboxes is not None:
                pred_bboxes = ops.scale_boxes(img.shape[2:], pred_bboxes.float(), orig_img.shape, padding=False)
            else:
                pred_bboxes = batched_mask_to_box(masks)
            # NOTE: SAM models do not return cls info. This `cls` here is just a placeholder for consistency.
            cls = torch.arange(len(pred_masks), dtype=torch.int32, device=pred_masks.device)
            idx = pred_scores > self.args.conf
            pred_bboxes = torch.cat([pred_bboxes, pred_scores[:, None], cls[:, None]], dim=-1)[idx]
            masks = masks[idx]
        results.append(Results(orig_img, path=img_path, names=names, masks=masks, boxes=pred_bboxes))
    # Reset segment-all mode.
    self.segment_all = False
    return results

def pre_transform(self, im):
    """
    Perform initial transformations on the input image for preprocessing.

    This method applies transformations such as resizing to prepare the image for further preprocessing.
    Currently, batched inference is not supported; hence the list length should be 1.

    Args:
        im (List[np.ndarray]): List containing a single image in HWC numpy array format.

    Returns:
        (List[np.ndarray]): List containing the transformed image.

    Raises:
        AssertionError: If the input list contains more than one image.

    Examples:
        >>> predictor = Predictor()
        >>> image = np.random.rand(480, 640, 3)  # Single HWC image
        >>> transformed = predictor.pre_transform([image])
        >>> print(len(transformed))
        1
    """
    assert len(im) == 1, "SAM model does not currently support batched inference"
    letterbox = LetterBox(self.args.imgsz, auto=False, center=False)
    return [letterbox(image=x) for x in im]

def preprocess(self, im):
    """
    Preprocess the input image for model inference.

    This method prepares the input image by applying transformations and normalization. It supports both
    torch.Tensor and list of np.ndarray as input formats.

    Args:
        im (torch.Tensor | List[np.ndarray]): Input image(s) in BCHW tensor format or list of HWC numpy arrays.

    Returns:
        (torch.Tensor): The preprocessed image tensor, normalized and converted to the appropriate dtype.

    Examples:
        >>> predictor = Predictor()
        >>> image = torch.rand(1, 3, 640, 640)
        >>> preprocessed_image = predictor.preprocess(image)
    """
    if self.im is not None:
        return self.im
    not_tensor = not isinstance(im, torch.Tensor)
    if not_tensor:
        im = np.stack(self.pre_transform(im))
        im = im[..., ::-1].transpose((0, 3, 1, 2))
        im = np.ascontiguousarray(im)
        im = torch.from_numpy(im)

    im = im.to(self.device)
    if not_tensor:
        im = (im - self.mean) / self.std
    im = im.half() if self.model.fp16 else im.float()
    return im

def prompt_inference(self, im, bboxes=None, points=None, labels=None, masks=None, multimask_output=False):
    """
    Perform image segmentation inference based on input cues using SAM's specialized architecture.

    This internal function leverages the Segment Anything Model (SAM) for prompt-based, real-time segmentation.
    It processes various input prompts such as bounding boxes, points, and masks to generate segmentation masks.

    Args:
        im (torch.Tensor): Preprocessed input image tensor with shape (N, C, H, W).
        bboxes (np.ndarray | List | None): Bounding boxes in XYXY format with shape (N, 4).
        points (np.ndarray | List | None): Points indicating object locations with shape (N, 2) or (N, num_points, 2), in pixels.
        labels (np.ndarray | List | None): Point prompt labels with shape (N) or (N, num_points). 1 for foreground, 0 for background.
        masks (np.ndarray | None): Low-res masks from previous predictions with shape (N, H, W). For SAM, H=W=256.
        multimask_output (bool): Flag to return multiple masks for ambiguous prompts.

    Returns:
        pred_masks (torch.Tensor): Output masks with shape (C, H, W), where C is the number of generated masks.
        pred_scores (torch.Tensor): Quality scores predicted by the model for each mask, with length C.

    Examples:
        >>> predictor = Predictor()
        >>> im = torch.rand(1, 3, 1024, 1024)
        >>> bboxes = [[100, 100, 200, 200]]
        >>> masks, scores, logits = predictor.prompt_inference(im, bboxes=bboxes)
    """
    features = self.get_im_features(im) if self.features is None else self.features

    prompts = self._prepare_prompts(im.shape[2:], self.batch[1][0].shape[:2], bboxes, points, labels, masks)
    return self._inference_features(features, *prompts, multimask_output)

@staticmethod
def remove_small_regions(masks, min_area=0, nms_thresh=0.7):
    """
    Remove small disconnected regions and holes from segmentation masks.

    This function performs post-processing on segmentation masks generated by the Segment Anything Model (SAM).
    It removes small disconnected regions and holes from the input masks, and then performs Non-Maximum
    Suppression (NMS) to eliminate any newly created duplicate boxes.

    Args:
        masks (torch.Tensor): Segmentation masks to be processed, with shape (N, H, W) where N is the number of
            masks, H is height, and W is width.
        min_area (int): Minimum area threshold for removing disconnected regions and holes. Regions smaller than
            this will be removed.
        nms_thresh (float): IoU threshold for the NMS algorithm to remove duplicate boxes.

    Returns:
        new_masks (torch.Tensor): Processed masks with small regions removed, shape (N, H, W).
        keep (List[int]): Indices of remaining masks after NMS, for filtering corresponding boxes.

    Examples:
        >>> masks = torch.rand(5, 640, 640) > 0.5  # 5 random binary masks
        >>> new_masks, keep = remove_small_regions(masks, min_area=100, nms_thresh=0.7)
        >>> print(f"Original masks: {masks.shape}, Processed masks: {new_masks.shape}")
        >>> print(f"Indices of kept masks: {keep}")
    """
    import torchvision  # scope for faster 'import ultralytics'

    if len(masks) == 0:
        return masks

    # Filter small disconnected regions and holes
    new_masks = []
    scores = []
    for mask in masks:
        mask = mask.cpu().numpy().astype(np.uint8)
        mask, changed = remove_small_regions(mask, min_area, mode="holes")
        unchanged = not changed
        mask, changed = remove_small_regions(mask, min_area, mode="islands")
        unchanged = unchanged and not changed

        new_masks.append(torch.as_tensor(mask).unsqueeze(0))
        # Give score=0 to changed masks and 1 to unchanged masks so NMS prefers masks not needing postprocessing
        scores.append(float(unchanged))

    # Recalculate boxes and remove any new duplicates
    new_masks = torch.cat(new_masks, dim=0)
    boxes = batched_mask_to_box(new_masks)
    keep = torchvision.ops.nms(boxes.float(), torch.as_tensor(scores), nms_thresh)

    return new_masks[keep].to(device=masks.device, dtype=masks.dtype), keep

def reset_image(self):
    """Reset the current image and its features, clearing them for subsequent inference."""
    self.im = None
    self.features = None

def set_image(self, image):
    """
    Preprocess and set a single image for inference.

    This method prepares the model for inference on a single image by setting up the model if not already
    initialized, configuring the data source, and preprocessing the image for feature extraction. It
    ensures that only one image is set at a time and extracts image features for subsequent use.

    Args:
        image (str | np.ndarray): Path to the image file as a string, or a numpy array representing
            an image read by cv2.

    Examples:
        >>> predictor = Predictor()
        >>> predictor.set_image("path/to/image.jpg")
        >>> predictor.set_image(cv2.imread("path/to/image.jpg"))

    Raises:
        AssertionError: If more than one image is attempted to be set.

    Notes:
        - This method should be called before performing inference on a new image.
        - The extracted features are stored in the `self.features` attribute for later use.
    """
    if self.model is None:
        self.setup_model()
    self.setup_source(image)
    assert len(self.dataset) == 1, "`set_image` only supports setting one image!"
    for batch in self.dataset:
        im = self.preprocess(batch[1])
        self.features = self.get_im_features(im)
        break

def set_prompts(self, prompts):
    """Set prompts for subsequent inference operations."""
    self.prompts = prompts

def setup_model(self, model=None, verbose=True):
    """
    Initialize the Segment Anything Model (SAM) for inference.

    This method sets up the SAM model by allocating it to the appropriate device and initializing the necessary
    parameters for image normalization and other Ultralytics compatibility settings.

    Args:
        model (torch.nn.Module | None): A pretrained SAM model. If None, a new model is built based on config.
        verbose (bool): If True, prints selected device information.

    Examples:
        >>> predictor = Predictor()
        >>> predictor.setup_model(model=sam_model, verbose=True)
    """
    device = select_device(self.args.device, verbose=verbose)
    if model is None:
        model = self.get_model()
    model.eval()
    model = model.to(device)
    self.model = model.half() if self.args.half else model.float()
    self.device = device
    self.mean = torch.tensor([123.675, 116.28, 103.53]).view(-1, 1, 1).to(device)
    self.std = torch.tensor([58.395, 57.12, 57.375]).view(-1, 1, 1).to(device)

    # Ultralytics compatibility settings
    self.model.pt = False
    self.model.triton = False
    self.model.stride = 32
    self.model.fp16 = self.args.half
    self.done_warmup = True
    self.torch_dtype = torch.float16 if self.model.fp16 else torch.float32

def setup_source(self, source):
    """
    Set up the data source for inference.

    This method configures the data source from which images will be fetched for inference. It supports
    various input types such as image files, directories, video files, and other compatible data sources.

    Args:
        source (str | Path | None): The path or identifier for the image data source. Can be a file path,
            directory path, URL, or other supported source types.

    Examples:
        >>> predictor = Predictor()
        >>> predictor.setup_source("path/to/images")
        >>> predictor.setup_source("video.mp4")
        >>> predictor.setup_source(None)  # Uses default source if available

    Notes:
        - If source is None, the method may use a default source if configured.
        - The method adapts to different source types and prepares them for subsequent inference steps.
        - Supported source types may include local files, directories, URLs, and video streams.
    """
    if source is not None:
        super().setup_source(source)

def get_im_features(self, im):
    """Extract image features from the SAM image encoder for subsequent processing."""
    assert isinstance(self.imgsz, (tuple, list)) and self.imgsz[0] == self.imgsz[1], (
        f"SAM 2 models only support square image size, but got {self.imgsz}."
    )
    self.model.set_imgsz(self.imgsz)
    self._bb_feat_sizes = [[x // (4 * i) for x in self.imgsz] for i in [1, 2, 4]]

    backbone_out = self.model.forward_image(im)
    _, vision_feats, _, _ = self.model._prepare_backbone_features(backbone_out)
    if self.model.directly_add_no_mem_embed:
        vision_feats[-1] = vision_feats[-1] + self.model.no_mem_embed
    feats = [
        feat.permute(1, 2, 0).view(1, -1, *feat_size) for feat, feat_size in zip(vision_feats, self._bb_feat_sizes)
    ]
    return {"image_embed": feats[-1], "high_res_feats": feats[:-1]}

def get_model(self):
    """Retrieve and initialize the Segment Anything Model 2 (SAM2) for image segmentation tasks."""
    from .build import build_sam  # slow import

    return build_sam(self.args.model)

def set_image(self, image):
    """
    Preprocess and set a single image for inference using the SAM2 model.

    This method initializes the model if not already done, configures the data source to the specified image,
    and preprocesses the image for feature extraction. It supports setting only one image at a time.

    Args:
        image (str | np.ndarray): Path to the image file as a string, or a numpy array representing the image.

    Examples:
        >>> predictor = SAM2Predictor()
        >>> predictor.set_image("path/to/image.jpg")
        >>> predictor.set_image(np.array([...]))  # Using a numpy array

    Raises:
        AssertionError: If more than one image is attempted to be set.

    Notes:
        - This method must be called before performing any inference on a new image.
        - The method caches the extracted features for efficient subsequent inferences on the same image.
        - Only one image can be set at a time. To process multiple images, call this method for each new image.
    """
    if self.model is None:
        self.setup_model(model=None)
    self.setup_source(image)
    assert len(self.dataset) == 1, "`set_image` only supports setting one image!"
    for batch in self.dataset:
        im = self.preprocess(batch[1])
        self.features = self.get_im_features(im)
        break

@smart_inference_mode()
def add_new_prompts(
    self,
    obj_id,
    points=None,
    labels=None,
    masks=None,
    frame_idx=0,
):
    """
    Add new points or masks to a specific frame for a given object ID.

    This method updates the inference state with new prompts (points or masks) for a specified
    object and frame index. It ensures that the prompts are either points or masks, but not both,
    and updates the internal state accordingly. It also handles the generation of new segmentations
    based on the provided prompts and the existing state.

    Args:
        obj_id (int): The ID of the object to which the prompts are associated.
        points (torch.Tensor, optional): The coordinates of the points of interest.
        labels (torch.Tensor, optional): The labels corresponding to the points.
        masks (torch.Tensor, optional): Binary masks for the object.
        frame_idx (int, optional): The index of the frame to which the prompts are applied.

    Returns:
        pred_masks (torch.Tensor): The flattened predicted masks.
        pred_scores (torch.Tensor): A tensor of ones indicating the number of objects.

    Raises:
        AssertionError: If both `masks` and `points` are provided, or neither is provided.

    Note:
        - Only one type of prompt (either points or masks) can be added per call.
        - If the frame is being tracked for the first time, it is treated as an initial conditioning frame.
        - The method handles the consolidation of outputs and resizing of masks to the original video resolution.
    """
    assert (masks is None) ^ (points is None), "'masks' and 'points' prompts are not compatible with each other."
    obj_idx = self._obj_id_to_idx(obj_id)

    point_inputs = None
    pop_key = "point_inputs_per_obj"
    if points is not None:
        point_inputs = {"point_coords": points, "point_labels": labels}
        self.inference_state["point_inputs_per_obj"][obj_idx][frame_idx] = point_inputs
        pop_key = "mask_inputs_per_obj"
    self.inference_state["mask_inputs_per_obj"][obj_idx][frame_idx] = masks
    self.inference_state[pop_key][obj_idx].pop(frame_idx, None)
    # If this frame hasn't been tracked before, we treat it as an initial conditioning
    # frame, meaning that the inputs points are to generate segments on this frame without
    # using any memory from other frames, like in SAM. Otherwise (if it has been tracked),
    # the input points will be used to correct the already tracked masks.
    is_init_cond_frame = frame_idx not in self.inference_state["frames_already_tracked"]
    obj_output_dict = self.inference_state["output_dict_per_obj"][obj_idx]
    obj_temp_output_dict = self.inference_state["temp_output_dict_per_obj"][obj_idx]
    # Add a frame to conditioning output if it's an initial conditioning frame or
    # if the model sees all frames receiving clicks/mask as conditioning frames.
    is_cond = is_init_cond_frame or self.model.add_all_frames_to_correct_as_cond
    storage_key = "cond_frame_outputs" if is_cond else "non_cond_frame_outputs"

    # Get any previously predicted mask logits on this object and feed it along with
    # the new clicks into the SAM mask decoder.
    prev_sam_mask_logits = None
    # lookup temporary output dict first, which contains the most recent output
    # (if not found, then lookup conditioning and non-conditioning frame output)
    if point_inputs is not None:
        prev_out = (
            obj_temp_output_dict[storage_key].get(frame_idx)
            or obj_output_dict["cond_frame_outputs"].get(frame_idx)
            or obj_output_dict["non_cond_frame_outputs"].get(frame_idx)
        )

        if prev_out is not None and prev_out.get("pred_masks") is not None:
            prev_sam_mask_logits = prev_out["pred_masks"].to(device=self.device, non_blocking=True)
            # Clamp the scale of prev_sam_mask_logits to avoid rare numerical issues.
            prev_sam_mask_logits.clamp_(-32.0, 32.0)
    current_out = self._run_single_frame_inference(
        output_dict=obj_output_dict,  # run on the slice of a single object
        frame_idx=frame_idx,
        batch_size=1,  # run on the slice of a single object
        is_init_cond_frame=is_init_cond_frame,
        point_inputs=point_inputs,
        mask_inputs=masks,
        reverse=False,
        # Skip the memory encoder when adding clicks or mask. We execute the memory encoder
        # at the beginning of `propagate_in_video` (after user finalize their clicks). This
        # allows us to enforce non-overlapping constraints on all objects before encoding
        # them into memory.
        run_mem_encoder=False,
        prev_sam_mask_logits=prev_sam_mask_logits,
    )
    # Add the output to the output dict (to be used as future memory)
    obj_temp_output_dict[storage_key][frame_idx] = current_out

    # Resize the output mask to the original video resolution
    consolidated_out = self._consolidate_temp_output_across_obj(
        frame_idx,
        is_cond=is_cond,
        run_mem_encoder=False,
    )
    pred_masks = consolidated_out["pred_masks"].flatten(0, 1)
    return pred_masks.flatten(0, 1), torch.ones(1, dtype=pred_masks.dtype, device=pred_masks.device)