Xinyuan Chang

Hello, I think there is no problem with the `adaptive weight`, the `out_features1+out_features2` is the old classes number in the current session and the `args.nb_cl` is the novel classes number...

@wonda You're right. I missed that.

> > > > > > > > @VictorLlu仅供参考，我打印了使用 8 个 GPU 进行训练时的数据预处理 (time1)、前向传播 (time2) 和反向传播 (time3) 的时间`mmengine/model/wrappers/distributed.py`。看来平均批处理时间较长的主要原因是某些迭代中的反向传播速度极慢。顺便问一下，您最近可以更新`nuscenes_converter_pon_centerline`文件吗？那会很有帮助！谢谢。 > > > > > > > > > > > >...