search

yigbt / deepFPlearn

Link molecular structures of chemicals (in form of topological fingerprints) with multiple targets
Other
8 stars 6 forks source link

Fixes needed for command line options in GNN code #25

Open bernt-matthias opened 11 months ago

bernt-matthias commented 11 months ago

The code starting here is essentially

    arguments = createArgsFromJson(
        opts.configFile, ignore_elements, return_json_object=False
    )
    opts = cp.args.TrainArgs().parse_args(arguments)
    mean_score, std_score = cp.train.cross_validate(args=opts, train_func=cp.train.run_training)

If I get it right: you always overwrite the command line arguments with the content from the json file. This should happen only if a json file is given.

ping @soulios