Method predict

sam2/sam2_image_predictor.py:225–288

Predict masks for the given input prompts, using the currently set image. Arguments: point_coords (np.ndarray or None): A Nx2 array of point prompts to the model. Each point is in (X,Y) in pixels. point_labels (np.ndarray or None): A length N array o

(
        self,
        point_coords: Optional[np.ndarray] = None,
        point_labels: Optional[np.ndarray] = None,
        box: Optional[np.ndarray] = None,
        mask_input: Optional[np.ndarray] = None,
        multimask_output: bool = True,
        return_logits: bool = False,
        normalize_coords=True,
    )

        return all_masks, all_ious, all_low_res_masks

    def predict(
        self,
        point_coords: Optional[np.ndarray] = None,
        point_labels: Optional[np.ndarray] = None,
        box: Optional[np.ndarray] = None,
        mask_input: Optional[np.ndarray] = None,
        multimask_output: bool = True,
        return_logits: bool = False,
        normalize_coords=True,
    ) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
        """
        Predict masks for the given input prompts, using the currently set image.

        Arguments:
          point_coords (np.ndarray or None): A Nx2 array of point prompts to the
            model. Each point is in (X,Y) in pixels.
          point_labels (np.ndarray or None): A length N array of labels for the
            point prompts. 1 indicates a foreground point and 0 indicates a
            background point.
          box (np.ndarray or None): A length 4 array given a box prompt to the
            model, in XYXY format.
          mask_input (np.ndarray): A low resolution mask input to the model, typically
            coming from a previous prediction iteration. Has form 1xHxW, where
            for SAM, H=W=256.
          multimask_output (bool): If true, the model will return three masks.
            For ambiguous input prompts (such as a single click), this will often
            produce better masks than a single prediction. If only a single
            mask is needed, the model's predicted quality score can be used
            to select the best mask. For non-ambiguous prompts, such as multiple
            input prompts, multimask_output=False can give better results.
          return_logits (bool): If true, returns un-thresholded masks logits
            instead of a binary mask.
          normalize_coords (bool): If true, the point coordinates will be normalized to the range [0,1] and point_coords is expected to be wrt. image dimensions.

        Returns:
          (np.ndarray): The output masks in CxHxW format, where C is the
            number of masks, and (H, W) is the original image size.
          (np.ndarray): An array of length C containing the model's
            predictions for the quality of each mask.
          (np.ndarray): An array of shape CxHxW, where C is the number
            of masks and H=W=256. These low resolution logits can be passed to
            a subsequent iteration as mask input.
        """
        if not self._is_image_set:
            raise RuntimeError("An image must be set with .set_image(...) before mask prediction.")

        # Transform input prompts

        mask_input, unnorm_coords, labels, unnorm_box = self._prep_prompts(point_coords, point_labels, box, mask_input,
                                                                           normalize_coords)

        masks, iou_predictions, low_res_masks = self._predict(
            unnorm_coords,
            labels,
            unnorm_box,
            mask_input,
            multimask_output,
            return_logits=return_logits,