Closed cww97 closed 3 years ago
Thanks for your question, The denominator is (k+1)
because we require the algorithm to output at least k
grasp poses.
This line has the same result with adding several zero-score grasp poses until there are k
grasp poses.
https://github.com/graspnet/graspnetAPI/blob/master/graspnetAPI/graspnet_eval.py#L195
why the denominator here is
(k+1)
instead of the length of score_list, or should this grids removed fromgrasp_accuracy