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

Error when running main.py under IMDBMulti dataset #8

Open
SaizhuoWang opened this issue May 23, 2019 · 2 comments
Open

Error when running main.py under IMDBMulti dataset #8

SaizhuoWang opened this issue May 23, 2019 · 2 comments

Comments

@SaizhuoWang
Copy link

SaizhuoWang commented May 23, 2019

Hi! Thank you very much for sharing the code.
Sorry to disturb, but I have met some problems when running main.py under IMDBMulti dataset. The program works fine under LINUX and AIDS700nef datasets. But it has some errors under IMDBMulti. My command is:

CUDA_VISIBLE_DEVICES=1 python main.py --dataset imdbmulti --gpu 1

There're 4 GTX 1080Ti GPUs on my server so I am sure the GPU I assigned is valid.
And after building the model, when the optimization started, the program errs. And the error messages are like this:
image
image
image
image
image
Sorry that I'm not quite familiar with tensorflow. Could you please tell me what the problem is? Thank you very much!

@yunshengb
Copy link
Owner

I see some error related to padding. Can you paste the entire configuration here? I suspect it is because of the max_nodes flag set wrongly. If you use config.py, we set it to 90 https://github.com/yunshengb/SimGNN/blob/master/model/Siamese/config.py#L20. If you manually provide command line arguments, make sure to add something like --max_nodes 90.

@yunshengb
Copy link
Owner

yunshengb commented Sep 27, 2019

The idea of creating config.py is to avoid typing in command line arguments. Instead, we can modify a few parameters in config.py and let the file handle the setting of the rest parameters via a bunch of if else statements. Then we can simply run python main.py without the following --xxxs. We apologize we did not make this idea clear. We have update the README accordingly. Thank you very much!

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