ibm / open-kg-canonicalization Goto Github PK

Hello!

First of all, thank you very much for your contribution @Dashdor @stevemar

I'm trying to run the code with the commands you proposed in the README, but I'm getting the following error:

Traceback (most recent call last): File "src/experiment.py", line 226, in <module> main() File "src/experiment.py", line 222, in main experiment = Experiment(args.data_id, args.data_dir, args.config_file, args.kge_algorithm, args.serialize_results) File "src/experiment.py", line 29, in __init__ self.openKG_canonicalize = OpenKGCanonicalization(data_dir, config_params_file, kge_algorithm, self.device).to(device=self.device) File "pathTo/Open-KG-canonicalization/src/canonicalize_learner.py", line 36, in __init__ models = self.load_models() File "pathTo/Open-KG-canonicalization/src/canonicalize_learner.py", line 65, in load_models if model_dir is None or not os.path.exists(model_dir): raise FileNotFoundError FileNotFoundError

Could you please help with that?

Thanks in advance.

Update: setup.py should be executed first before running any commands. Could it be added to README as well?

First of all, thank you very much for your code.
But I have a question about some of your files. Could you please tell me how the pkl files in Open-KG-canonicalization/data/vae_run/ReVerb45k_hac_OKG_canonicalize_heads/ are obtained.
Thanks a lot.