Method augment

tensorpack/dataflow/imgaug/base.py:183–200

Create a transform, and apply it to augment the input image. This can save you one line of code, when you only care the augmentation of "one image". It will not return the :class:`Transform` object to you so you won't be able to apply the same transformation on

(self, img)

                                apply_coords=lambda coords: legacy_augment_coords(self, coords, p))

    def augment(self, img):
        """
        Create a transform, and apply it to augment the input image.

        This can save you one line of code, when you only care the augmentation of "one image".
        It will not return the :class:`Transform` object to you
        so you won't be able to apply the same transformation on
        other data associated with the image.

        Args:
            img (ndarray): see notes of this class on the requirements.

        Returns:
            img: augmented image.
        """
        check_dtype(img)
        t = self.get_transform(img)
        return t.apply_image(img)

    # ###########################
    # Legacy interfaces: