Maksym Tymkovych

Hi there, I am having the same issue as all user in that thread. Could you please help us?

How has anyone solved this problem? In my case, there is no _nan_ directly, but there is assert. ``` cost_giou = -generalized_box_iou(box_cxcywh_to_xyxy(out_bbox), box_cxcywh_to_xyxy(tgt_bbox)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ``` ``` assert (boxes1[:, 2:] >=...

> How has anyone solved this problem? In my case, there is no _nan_ directly, but there is assert. > > ``` > cost_giou = -generalized_box_iou(box_cxcywh_to_xyxy(out_bbox), box_cxcywh_to_xyxy(tgt_bbox)) > ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ >...

How many classes are in the dataset, and which class is numbered (started from 0-index, 1-index)?