goldentimecoolk
goldentimecoolk
> me too ,I trained it on cub.It is worse than Resnet50,I don't know why? It's worth to figure out the reason, which might largely result from the difference of...
> can you share to me about your code?perhaps something wrong in my code I had the same result as you, i.e. a worse performance than Resnet50 backbone. The main...
> 请问下 显示我已成功编译DCN 为什么还是没有GPU @xiaoaliu 我有同样的问题，请问您解决了吗？
I test with the pytorch model, it is normal with all above scales.
The problem is solved in the [issue](https://github.com/open-mmlab/mmdeploy/issues/2601).
Hi @yinfan98, I think it is not the custom ops. I want to fetch more information other than `dets` and `labels` from the existing pretrained model.
我也遇到了同样的问题，请问你解决了吗？ ------------- 问题已解决： 直接对txt压缩，不要对txt的文件夹压缩
It is a problem of the mmdeploy version. I solved it by using the version 0.14.0.