divelab / GOOD

GOOD: A Graph Out-of-Distribution Benchmark [NeurIPS 2022 Datasets and Benchmarks]
https://good.readthedocs.io/
GNU General Public License v3.0
180 stars 19 forks source link

Question about dataset #25

Closed bruno686 closed 6 months ago

bruno686 commented 6 months ago

Hi GOOD team, I see that when mode is test, it is a direct read out of the pt file, which contains the test results. This seems different from the normal form, which I've seen in the past is reading the model and loading the data, then making predictions. That means that the pt only contains the model and not the results, how should I adjust it like that? Thanks!

Best regards,