babble2
babble2
about 15h with a 3090 during the pre-training, and fine-tuning about 3 hours
> 88.9四舍五入不就是89么,我拿作者公布的权重测试在total-text上的f分数为88.69
> > @reno77 wan I have the same issue to run the demo.py on a video. Have you solved it? > > I've updated the demo_idol.py from [lalalafloat](https://github.com/lalalafloat) to visualize...
i meet same problems too, how do you solve it ?
> I tried to eval the model with R50 backbone trained on OVIS dataset, but the inference time seems to be meet some problems as below: > > ``` >...
me too