Ming Li

> We have no plan to release this code for now. We will consider releasing the code of this large model after this paper gets peer-reviewed. Stay tuned! Thank you...

> > We have no plan to release this code for now. We will consider releasing the code of this large model after this paper gets peer-reviewed. Stay tuned! Thank...

> Could you provide a config so that we can reproduce the error? Hi, @ZwwWayne I have same issue too, it can be fixed by changing [this line](https://github.com/open-mmlab/mmdetection/blob/240d7a31c745578aa8c4df54c3074ce78b690c34/mmdet/models/roi_heads/mask_heads/fused_semantic_head.py#L104) to: ```...

> Hello @mitming Could you provide the version of mmdetection and mmselfsup you used? I would like to reproduce this bug and explore the problem. @jbwang1997 Thanks a lot! Please...

@jbwang1997 Thanks for your answer, in my experiment, this bug also affects other methods like mask-rcnn/fcos/retinanet, could you please check again?

> This bug needs to be fixed in mmselfsup, It's better also to report it there. > > BTW, this bug will not occurs if you use the newest mmdet...

> Hi @mitming. I'm trying to figure out the problem. It may take some time. If I find out the problem, I will report the results in this issue as...

Hi @ZwwWayne, Could you please help me since there is no reply from @BIGWangYuDong ?

Hi, @YuanLiuuuuuu Please check [this issue](https://github.com/open-mmlab/mmdetection/issues/8762) for more information.

> Could you please provide all these config files, which fail to converge? @YuanLiuuuuuu DETR and Deformable DETR fail to converge, other methods (fcos/mask-rcnn/retinanet) have lower performance under same machine...