shuimushan

I ran the run_flops.dist and got the warnings below: WARNING:root:Skipped operation aten::layer_norm 76 time(s) WARNING:root:Skipped operation aten::mul_ 152 time(s) WARNING:root:Skipped operation aten::gelu 114 time(s) WARNING:root:Skipped operation aten::upsample_nearest2d 22 time(s) WARNING:root:Skipped...

Thanks for your excellent work! I'd like to utilize the dataset in a different way and don't know how to get the annotations as you have provided. Could you share...

I print model.info for both the checkpoint files you provided (FastSAM_X.pt & FastSAM_S.pt) and the files downloaded from [yolov8](https://docs.ultralytics.com/zh/models/yolov8/#__tabbed_1_3) (yolov8s-seg.pt & yolov8x-seg.pt). Then get different parameters as listed below. Why...

您好！请问TartanAir、RobotCar、Nordland这三种数据集都是分开训练的吗？在每种数据集里划分了不同环境实现了单个数据集的终身学习，有没有尝试过把不同数据集合并在一起进行终身学习呀？