Function _check_tap_actions_match

eval/utils/action_utils.py:183–211

Determines if two tap actions are the same.

(
    tap_1_yx,
    tap_2_yx,
    annotation_positions,
    matching_tap_distance_threshold_screen_percentage,
    annotation_width_augment_fraction,
    annotation_height_augment_fraction,
)

def _check_tap_actions_match(
    tap_1_yx,
    tap_2_yx,
    annotation_positions,
    matching_tap_distance_threshold_screen_percentage,
    annotation_width_augment_fraction,
    annotation_height_augment_fraction,
):
    """Determines if two tap actions are the same."""
    resized_annotation_positions = _resize_annotation_bounding_boxes(
        annotation_positions,
        annotation_width_augment_fraction,
        annotation_height_augment_fraction,
    )

    # Check if the ground truth tap action falls in an annotation's bounding box.
    tap1_in_box = _yx_in_bounding_boxes(tap_1_yx, resized_annotation_positions)
    tap2_in_box = _yx_in_bounding_boxes(tap_2_yx, resized_annotation_positions)
    both_in_box = jnp.max(tap1_in_box & tap2_in_box)

    # If the ground-truth tap action falls outside any of the annotation
    # bounding boxes or one of the actions is inside a bounding box and the other
    # is outside bounding box or vice versa, compare the points using Euclidean
    # distance.
    within_threshold = (
        jnp.linalg.norm(jnp.array(tap_1_yx) - jnp.array(tap_2_yx))
        <= matching_tap_distance_threshold_screen_percentage
    )
    return jnp.logical_or(both_in_box, within_threshold)


def _check_drag_actions_match(