You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I set batch size to 32, if i turn box_list_iou into cpu mode, gpu memory consumption is only 6GB for each of two gpus, but when turning box_list_iou into gpu mode, it would grow up and finally out of memory.
I found out that memory leak may happen in
box_list_iou
(https://github.com/zhangxiaosong18/FreeAnchor/blob/master/maskrcnn_benchmark/modeling/rpn/free_anchor_loss.py#L108)when it processes large number of ground truth, of course the gpu memory grows up. but it never frees the memory it holds.
turning to cpu mode is a workaround but very slow.
The text was updated successfully, but these errors were encountered: