Jiaxuan comments

Results 7 comments of


                                            Jiaxuan

run_batch.sh

Thanks for spotting this bug. I have been using the Linux development environment, and sometimes got sloppy of using `/` in the path (should be replaced by `os.path.join()`). I'll post...

Unable to run the test program

Hi Sumit, Very likely you are not using python3. “@“ is only introduced in python3 as matrix multiplication. Best, Jiaxuan Original Message Sender:Sumit [email protected] Recipient:snap-stanford/[email protected] Cc:[email protected]; [email protected] Date:Sunday, Jul 1,...

Unable to run the test program

seems that you are not properly installing pytorch cuda version. ' torch.cuda.FloatTensor is not enabled' Original Message Sender:Sumit [email protected] Recipient:snap-stanford/[email protected] Cc:[email protected]; [email protected] Date:Monday, Jul 2, 2018 14:55 Subject:Re: [snap-stanford/GraphRNN] Unable...

Question about ID-GNN

Hi, thanks for your interest in ID-GNN. 1. For node classification, the configs are here: https://github.com/snap-stanford/GraphGym/blob/master/run/grids/IDGNN/node.txt 2. Yes, that means ID-GNN fast 3. The node identity feature is computed via...

About Scenario 2

Thanks for the question. This is a good feature request. Currently, I recommend trying out the design space of 96 GNN models, shown here: https://github.com/snap-stanford/GraphGym/blob/master/run/grids/example.txt You could take a look...

Some questions for utilys.py

Hi, thanks for the question. 1. Yes indeed, that's another version of anchor-set selection. You can commented in out or play around with it. 2. Yes, the reason is that...

Importing Graphgym Causes segmentation fault (and std::bad_alloc())

This is a weird error I haven't encountered before. It will be great if you can pinpoint where the segmentation fault error occurs. Also, based on your description, you may...