Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How are planes labeled in the plane segmentation mask branch? #26

Open
sheMnapion opened this issue Jul 24, 2019 · 2 comments
Open

How are planes labeled in the plane segmentation mask branch? #26

sheMnapion opened this issue Jul 24, 2019 · 2 comments

Comments

@sheMnapion
Copy link

Hi, I have read your paper, but I'm confused about the way the planes are labeled from 1 to 10 (if 10 planes are found), and I haven't got a clue for that. Are they labeled according to the order of their covered area, or from left top to right bottom, or just labeled randomly?

@sheMnapion sheMnapion changed the title How are planes labeled in the label segmentation mask branch? How are planes labeled in the plane segmentation mask branch? Jul 24, 2019
@art-programmer
Copy link
Owner

They are random. The order of planes doesn't matter since I used the matching loss.

@skq-5233
Copy link

They are random. The order of planes doesn't matter since I used the matching loss.

Great work!
when I try to train the network an error shows up: NotFoundError: ./tf_nndistance_so.so: undefined symbol: _ZTIN10tensorflow8OpKernelE.
I think this may be because I didn't successfully build the code.
How can I eliminate this problem?
ubuntu :16.04 ; nvidia-driver-440;cuda:10.0; cudnn:7.5.0; tensorflow-gpu:1.10.0; gcc/g++:5.4.0;
Thanks in advance!!! @art-programmer

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants