Peyton
Hi, @fairy149, your picture was not uploaded successfully. Plus, using English is more appreciated for better community discussion around the world.
Can you provide the detailed information, such as the version of cuda / cudnn / torch. And can you provide details of the command to perform your experiment?
This document might be helpful to you. https://mmdetection.readthedocs.io/en/latest/tutorials/customize_dataset.html#modify-dataset-classes
Hi, @Audrey528 Can you provide the full config?
Hi, @Audrey528 As for the second question, I think there is no need to change this part config, because the distiller have nothing to do with the number of classes.
> Hello. How did you install mmdet? After I installed it according to the official tutorial, I still reported an error in the train_mmdet.py file. @xuhao-anhe hi, sorry for my...
Hi, thank you for your attention. You can refer to [DetNAS](https://github.com/open-mmlab/mmrazor/blob/master/configs/nas/detnas/README.md), which uses both SPOS from MMRazor and MMDet.
Hi, @Audrey528, MMRazor currently can not be used in mmdet. On the contrary, you could implement mmdet in mmrazor. In mmrazor, you should add `mmdet` prefix to get mmdet's registry....
Hi, @sunanlin13174 , thank you for your advice! We will add this requirement to the backlog.
请检查2007_train.txt是否存在内容