Bo Sun
Bo Sun
Hi, having the same problem here. Problem can not solved by this command `pip install --ignore-installed --upgrade pip setuptools` documented in your documentation.
Thanks! Do you mind leaving me your preferred contact app so I can connect with you and discuss about qtpylib.
I see, thanks. I notice fsdet's current data loader is loading 1 instance per image for shot data. For example, 3 shots (maybe different categories) are coming from the same...
Which base training checkpoint (`model_final.pth`) you are using? You train it yourself or downloaded from FsDet.
@Retiina @yhcao6 Hi guys, will you be able to reproduce the nAP for 10shot PASCAL VOC split1?
those shots are unstable and can have large variance in different run. please try if 5-shot and 10-shot can be reproduced, another thread finds not, if so, we need to...
> What if I only use 1 gpu? Will this affect the result? > In addition, the config file shows that the backbone seems to be trained. >  >...
> @bsun0802 , there is the result of split1 10shot of FSCE, still lower than paper > > ``` > [03/29 16:10:55 fsdet.evaluation.pascal_voc_evaluation]: Evaluating voc_2007_test_all1 using 2007 metric. Note that...
@yhcao6 Seems odd. I would say above 62.6 should be easy to reach. We will have time to inspect that until this weekend.
In your provided test scripts, you set meta-test=True. Is this really directly comparable to TFA? Correct me if I'm wrong.