Method apply_box

PATH/core/data/transforms/seg_transforms_dev.py:106–134

Apply the transform on an axis-aligned box. By default will transform the corner points and use their minimum/maximum to create a new axis-aligned box. Note that this default may change the size of your box, e.g. after rotations. Args: box (ndarr

(self, box: np.ndarray)

        return self.apply_image(segmentation)

    def apply_box(self, box: np.ndarray) -> np.ndarray:
        """
        Apply the transform on an axis-aligned box. By default will transform
        the corner points and use their minimum/maximum to create a new
        axis-aligned box. Note that this default may change the size of your
        box, e.g. after rotations.

        Args:
            box (ndarray): Nx4 floating point array of XYXY format in absolute
                coordinates.
        Returns:
            ndarray: box after apply the transformation.

        Note:
            The coordinates are not pixel indices. Coordinates inside an image of
            shape (H, W) are in range [0, W] or [0, H].

            This function does not clip boxes to force them inside the image.
            It is up to the application that uses the boxes to decide.
        """
        # Indexes of converting (x0, y0, x1, y1) box into 4 coordinates of
        # ([x0, y0], [x1, y0], [x0, y1], [x1, y1]).
        idxs = np.array([(0, 1), (2, 1), (0, 3), (2, 3)]).flatten()
        coords = np.asarray(box).reshape(-1, 4)[:, idxs].reshape(-1, 2)
        coords = self.apply_coords(coords).reshape((-1, 4, 2))
        minxy = coords.min(axis=1)
        maxxy = coords.max(axis=1)
        trans_boxes = np.concatenate((minxy, maxxy), axis=1)
        return trans_boxes

    def apply_polygons(self, polygons: list) -> list:
        """