def evaluate_main_modified(dataset):
args, train_args = _parse_args_modified(dataset)
print("train_args:\n", train_args)
# TODO do this argument transfering in the load_train_args instead of train.py, evaluate.py, ensemble_evaluate.py
train_args.checkpoint_model_num = args.checkpoint_model_num
train_args.entity_extension = args.entity_extension
train.args = args
args.batch_size = train_args.batch_size
printPredictions = None
if args.print_predictions:
from evaluation.print_predictions import PrintPredictions
printPredictions = PrintPredictions(
config.base_folder + "data/tfrecords/" + args.experiment_name +
"/", args.predictions_folder, args.entity_extension,
args.gm_bucketing_pempos, args.print_global_voters,
args.print_global_pairwise_scores)
return printPredictions
'_z_') if args.el_datasets != "" else None
args.ed_val_datasets = [int(x) for x in args.ed_val_datasets.split('_')]
args.el_val_datasets = [int(x) for x in args.el_val_datasets.split('_')]
args.gm_bucketing_pempos = [
int(x) for x in args.gm_bucketing_pempos.split('_')
] if args.gm_bucketing_pempos else []
print(args)
return args, train_args
if __name__ == "__main__":
args, train_args = _parse_args()
# TODO do this argument transfering in the load_train_args instead of train.py, evaluate.py, ensemble_evaluate.py
train_args.checkpoint_model_num = args.checkpoint_model_num
train_args.entity_extension = args.entity_extension
train.args = args
args.batch_size = train_args.batch_size
printPredictions = None
if args.print_predictions:
from evaluation.print_predictions import PrintPredictions
printPredictions = PrintPredictions(
config.base_folder + "data/tfrecords/" + args.experiment_name +
"/", args.predictions_folder, args.entity_extension,
args.gm_bucketing_pempos, args.print_global_voters,
args.print_global_pairwise_scores)
from model.util import Tee
tee = Tee(args.output_folder + 'evaluate-log.txt', 'a')
print("train_args:\n", train_args)
evaluate()
args.predictions_folder):
os.makedirs(args.predictions_folder)
if args.predictions_folder is not None and not os.path.exists(
args.predictions_folder + "ed/"):
os.makedirs(args.predictions_folder + "ed/")
if args.predictions_folder is not None and not os.path.exists(
args.predictions_folder + "el/"):
os.makedirs(args.predictions_folder + "el/")
args.output_folder = []
for training_name, prefix in zip(args.training_name,
args.all_spans_training):
args.output_folder.append(config.base_folder+"data/tfrecords/" + \
args.experiment_name+"/{}training_folder/".format(prefix) + \
training_name+"/")
args.batch_size = 1
print(args)
return args
if __name__ == "__main__":
args = _parse_args()
printPredictions = None
if args.predictions_folder is not None:
from evaluation.print_predictions import PrintPredictions
printPredictions = PrintPredictions(
config.base_folder + "data/tfrecords/" + args.experiment_name +
"/", args.predictions_folder)
evaluate()