nieyan

Hi , Even What a great job! And I want ask you that do you find any outstanding point of this two detection model design ways ? Which is better...

https://github.com/Tramac/Lightweight-Segmentation/blob/71bf91f3d5b946a046becfd5d8667e8a0f80d630/light/model/mobilenetv3_seg.py#L17 It should be: inter_channels = 112 if mode == 'large' else 24 by the way, mode == 'small' might be wrong too

If training with **usegpu=False** , will throw assert error of size_average.

choose of fisheye model

4

Thanks for your great work. I am confused of which fisheye model is better ? How to make the dicision? My camera's FOV is 195 x 150

没找到地图合并的功能

14

使用docker的纯cpu环境启动，参考文档： https://github.com/w111liang222/lidar-slam-detection/blob/main/docs/slam.md 正常建图完成，进editor界面打开了上述建好的地图； 并copy了一份在 /media/lp_log/map目录下，想使用两份map测试地图合并功能，但是网页上好像没有这个选项？