search

Shen-Lab / GraphCL_Automated

[ICML 2021] "Graph Contrastive Learning Automated" by Yuning You, Tianlong Chen, Yang Shen, Zhangyang Wang; [WSDM 2022] "Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations" by Yuning You, Tianlong Chen, Zhangyang Wang, Yang Shen
108 stars 11 forks source link

error when running semisupervised_OGB #8

Open jet955 opened 7 months ago

jet955 commented 7 months ago

Hello,

Thank you for this awesome work! I tried to run the pretraining code in the semisupervised setting by running this command (python main_pretrain_graphcl_joao.py --gamma 0.01 --dataset ogbg-molchembl) and it gave this error:

"FileNotFoundError: [Errno 2] No such file or directory: 'dataset/ogbg_molchembl/mapping/typeidx2type.csv.gz'"

I checked my dataset/ogbg_molchembl/mapping directory and it only contains the "mol.csv.gz" file but not typeidx2type.csv.gz and attridx2attr.csv.gz files. Could you please let me know how I can get these two files?

yyou1996 commented 5 months ago

Hi,

I suspect this results from the inconsistency of the OGB version, which was 1.2.4 (https://github.com/Shen-Lab/GraphCL_Automated#dependencies). It should execute the dataset downloading, as I glance their repo https://github.com/search?q=repo%3Asnap-stanford%2Fogb%20typeidx2type.csv.gz&type=code.

Would you might also open an issue in OGB, if there is still problems?