Closed zhengye1995 closed 3 years ago
A possible solution is applying this fix https://github.com/open-mmlab/mmdetection/pull/3702 to gfl_head.py.
if len(pos_inds) == 0: weight_targets become 0, avg_factor may become 0, resulting in nan.
Hello,do you fix the issue? https://github.com/shinya7y/UniverseNet/issues/13
I updated the master branch with the abovementioned fix. If the issue persists, please let me know more details.
I updated the master branch with the abovementioned fix. If the issue persists, please let me know more details.
Thanks for your replay, it works. But I still need to reduced the learning rate and tried to increase the warm-up step, which may results in the performance is not well.
I close this issue. If there are performance issues (e.g., lower AP than the baselines ATSS and GFL), please open another issue.
Hello, thanks for your outstanding work!
I want to train universeNet with the images which do not contain objects, so I set filter_empty_gt=False, but the loss is nan.
I have reduced the learning rate and tried to increase the warm-up step, but they are not work.
I have also tried to train my data with other models like cascade rcnn or faster rcnn with the same setting, the losses for them are both normal.
So, how can i fix this issue?