zhenghao977 / FCOS-PyTorch-37.2AP

A pure torch implement of FCOS 37.2AP
162 stars 39 forks source link

A confusing line of code, which may have to be modified #24

Open shawnfd opened 2 years ago

shawnfd commented 2 years ago

Hi zhenghao, the train/eval mode of the fcos model is written in your code [path/model/fcos.py], however, in the line 26 'super().train(mode=True)', the model mode is fixed as training mode. That leads to some unexpected inference results when doing inference by set model to eval(). So, I suggest modify 'super().train(mode=True)' to 'super().train(mode=mode)'. Otherwise, the dropout/bn is not locked in the inference procedure. At the same time, the dropout/bn status can be affected by the [path/model/config.py] configurations: freeze_stage1/freeze_bn

zhenghao977 commented 2 years ago

这是来自QQ邮箱的假期自动回复邮件。   您好,我最近正在休假中,无法亲自回复您的邮件。我将在假期结束后,尽快给您回复。