search

fanq15 / FewX

FewX is an open-source toolbox on top of Detectron2 for data-limited instance-level recognition tasks.
https://github.com/fanq15/FewX
MIT License
346 stars 48 forks source link

Support set for base classes and Limit on no. of ways #33

Open anujstam opened 3 years ago

anujstam commented 3 years ago

Hello. I'm attempting to use a different dataset with the AttentionRPN. The evaluation script uses the pickled dataframe of the 10-shot novel classes, so when I evaluate, it detects only novel classes.

If I create a 10-shot support DF of the base classes and use that, I am able to detect the same. Is this the intended way of evaluating the base classes or have I done something incorrectly? I presume in the final evaluation of novel+base, another support DF needs to be created?

Also - there are places where the no. of ways are fixed to 2 and this is asserted. Is it safe to remove those assertions?

tailororrr commented 2 years ago

我也有同样的问题，当我基础类训练完成后，进行测试时，只能检测到新类的结果，基础类都是0.00