Zhijie Wang

Hi there, I just tested your pretrained model on test set, and the result is close to the value reported in paper. However, when I tested on validation dataset, it...

> @paulwong16 > > Because we choose the best model for the test set instead of the validation set. but why CD on test set could be even much lower...

> @paulwong16 > > Because the pretrained model is best for fitting distribution of the testing set. > > Instead, the distribution of the training and validation set may be...

@JoyBeginner 的方法在Ubuntu16.04下是有效的，thx。 另：ubuntu下tex live默认配置编译后生成的pdf里，章节名称缺少数字序号。暂未找到具体原因。解决方案是打开terminal在编译一遍：`xelatex main.tex`

I think is straightforward to derive m12 and m45, for m23 pls refer to (36) (37) in Sec V Sub-sec E. Best,

> Thanks for your excellent work. > > I have two suggestions for improving this package: > > 1. To facilitate the followers, the developers are encouraged to provide an...

> 請問能不能也發給我example rosbag 試看看(我用自己錄的rosbag誤差很大) > 請放在這個google drive 上: > https://drive.google.com/drive/folders/1rbIeLl8nRSY3FBXGcIrFKFFIner1PYc9?usp=sharing was uploaded.

> The output gives x,y, and yaw. Is there a way to determine z between the lidar and odom Sorry for the late reply, adding another dimension where totally change...

Try more straight-line motion when recording the rosbag. (I think there is somewhere discussing the effects of choosing different paths in Censi's paper.)