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

in_degree and out_degree #16

Closed
Jihao-Li opened this issue Sep 24, 2019 · 5 comments
Closed

in_degree and out_degree #16

Jihao-Li opened this issue Sep 24, 2019 · 5 comments

Comments

@Jihao-Li
Copy link

It is illustrated in figure 2 in origin paper that there are 3 input degrees and 4 output degrees in node operation. In a random graph, we can not guarantee the degree of a node. Is it just a analogy?

@seungwonpark
Copy link
Owner

Yes, figure 2 is just an example of nodes in random graph.

@Jihao-Li
Copy link
Author

Thank you!

@Jihao-Li
Copy link
Author

In original paper, the author said that input node and output node were excluded. So, there should be 34 nodes in one stage. But I counted the number of nodes in figure 1 in a stage. I found that there are only 33 nodes in one stage. That's to say, the input node was not excluded. Only the output node was excluded. Do I understand correctly?

@seungwonpark
Copy link
Owner

Sorry, I don't know for sure about that. But I don't think the number of nodes won't matter much here since 34 and 33 don't differ much.

@Jihao-Li
Copy link
Author

How many hours did you use? I saw you said that you used 16 hours on V100. Did you use a single V100? Did you use 1281167 images or 1231167 images?

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

2 participants