PRBonn / LiDAR-MOS

(LMNet) Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data (RAL/IROS 2021)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

multi residual_images, parameters about n_input_scans? thanks!

emilyemliyM opened this issue · comments

Dear author ,

I see that it uses 8 residual_imgs in the paper,

So I also want to use 8 images.

But I don't know how to use about the 'n_input_scans' in the code.

Does "n_input_scans" mean that the multi_residual_image?

image

Yes, 'n_input_scans' is to set the number of residual images you want use. You could set it in the config files.

Yes, 'n_input_scans' is to set the number of residual images you want use. You could set it in the config files.
Thanks for reply!!!!! Happy new year of the tiger.
So I need use "current_index = start_index + self.n_input_scans - 1 "
instead of
"current_index = start_index"

Similarly,
use "for index in range(start_index, start_index + self.n_input_scans): "
not "for index in range(start_index, start_index + 1)"

Happy New Year!

Yes, we use 'start_index + self.n_input_scans' to avoid loading the beginning of sequences where there are no residual images available.

Since this issue is duplicated with #41, I would close this one, and let's keep track of #41.