i find that something wrong with find_nearest method,One of the reasons why kdtree saves time is to use the distance from the nearest point to the point to be queried as the radius. If there is no intersection with the hyperplane, you do not need to go to the sibling nodes again. However, this method does not have this crucial step。
i find that something wrong with find_nearest method,One of the reasons why kdtree saves time is to use the distance from the nearest point to the point to be queried as the radius. If there is no intersection with the hyperplane, you do not need to go to the sibling nodes again. However, this method does not have this crucial step。