Loading pre-trained model weights fails.

Open Sillouevan opened this issue 1 year ago • 1 comments

Hello! When I try to follow the command CUDA_VISIBLE_DEVICES=2 python test.py GGNN GraphBinaryClassification ../data/data/data/cve/badall --storedModel_path "./trained_model/GGNN_GraphBinaryClassification__2023-02-01_05-36-00_f1 = 0.800_best.pkl", one issue occurred. The details are as follows： It mentioned error! in traububg_utils.py line199. Does it mean cli_data_hyperparameter_overrides=args.data_param_override, line 199 in file training_utils.py? So how can I solve this problem? And is this the reason why loading pre-trained model weights fails? Looking forward to your reply : ).

May 12 '24 06:05 Sillouevan

Hi, sorry for the late reply. It looks like the issue is due to the model not being loaded correctly here. Could you please provide more detailed information or bug details when executing this function?

Jun 17 '24 20:06 HuantWang