Function check_actions_match

eval/utils/action_utils.py:235–319

Determines if two actions are considered to be the same. Two actions being "the same" is defined here as two actions that would result in a similar screen state. Args: action_1_touch_yx: The (y, x) coordinates of the first action's touch. action_1_lift_yx: The (y, x) co

(
    action_1_touch_yx,
    action_1_lift_yx,
    action_1_action_type,
    action_2_touch_yx,
    action_2_lift_yx,
    action_2_action_type,
    annotation_positions,
    tap_distance_threshold = _TAP_DISTANCE_THRESHOLD,
    annotation_width_augment_fraction = ANNOTATION_WIDTH_AUGMENT_FRACTION,
    annotation_height_augment_fraction = ANNOTATION_HEIGHT_AUGMENT_FRACTION,
)

def check_actions_match(
    action_1_touch_yx,
    action_1_lift_yx,
    action_1_action_type,
    action_2_touch_yx,
    action_2_lift_yx,
    action_2_action_type,
    annotation_positions,
    tap_distance_threshold = _TAP_DISTANCE_THRESHOLD,
    annotation_width_augment_fraction = ANNOTATION_WIDTH_AUGMENT_FRACTION,
    annotation_height_augment_fraction = ANNOTATION_HEIGHT_AUGMENT_FRACTION,
):
    """Determines if two actions are considered to be the same.

    Two actions being "the same" is defined here as two actions that would result
    in a similar screen state.

    Args:
        action_1_touch_yx: The (y, x) coordinates of the first action's touch.
        action_1_lift_yx: The (y, x) coordinates of the first action's lift.
        action_1_action_type: The action type of the first action.
        action_2_touch_yx: The (y, x) coordinates of the second action's touch.
        action_2_lift_yx: The (y, x) coordinates of the second action's lift.
        action_2_action_type: The action type of the second action.
        annotation_positions: The positions of the UI annotations for the screen. It
            is A 2D int array of shape (num_bboxes, 4), where each row represents a
            bounding box: (y_top_left, x_top_left, box_height, box_width). Note that
            containment is inclusive of the bounding box edges.
        tap_distance_threshold: The threshold that determines if two taps result in
            a matching screen state if they don't fall the same bounding boxes.
        annotation_width_augment_fraction: The fraction to increase the width of the
            bounding box by.
        annotation_height_augment_fraction: The fraction to increase the height of
            of the bounding box by.

    Returns:
        A boolean representing whether the two given actions are the same or not.
    """
    action_1_touch_yx = jnp.asarray(action_1_touch_yx)
    action_1_lift_yx = jnp.asarray(action_1_lift_yx)
    action_2_touch_yx = jnp.asarray(action_2_touch_yx)
    action_2_lift_yx = jnp.asarray(action_2_lift_yx)

    # Checks if at least one of the actions is global (i.e. not DUAL_POINT),
    # because if that is the case, only the actions' types need to be compared.
    has_non_dual_point_action = jnp.logical_or(
        _is_non_dual_point_action(action_1_action_type),
        _is_non_dual_point_action(action_2_action_type),
    )

    different_dual_point_types = jnp.logical_xor(
        is_tap_action(action_1_touch_yx, action_1_lift_yx),
        is_tap_action(action_2_touch_yx, action_2_lift_yx),
    )

    is_tap = jnp.logical_and(
        is_tap_action(action_1_touch_yx, action_1_lift_yx),
        is_tap_action(action_2_touch_yx, action_2_lift_yx),