wangbo9719
commented
2 years ago You can refer to the closed issue #1 to generate the new_dev.dict for your own dataset.
Closed tideng777 closed 2 years ago
wangbo9719
commented
2 years ago You can refer to the closed issue #1 to generate the new_dev.dict for your own dataset.
Hi Guy, good job. I met some problem when I try to run my dataset. I wanna know How to generate the _newdev.dict?
I use "--do_eval" in link prediction, it will show an error below: Traceback (most recent call last): File "run_link_prediction.py", line 4, in
main()
File "/data2/lidj/projects/StAR_KGC/StAR/link_prediction/train.py", line 950, in main
train(args, train_dataset, model, tokenizer, eval_dataset=dev_dataset, eval_fn=evaluate_pairwise_ranking)
File "/data2/lidj/projects/StAR_KGC/StAR/kbc/utils_fn.py", line 279, in train
args, eval_dataset, model, tokenizer, global_step=global_step, fileprefix="eval")
File "/data2/lidj/projects/StAR_KGC/StAR/link_prediction/train.py", line 625, in evaluate_pairwise_ranking
dev_dict = torch.load("./data/" + args.dataset + "/new_dev.dict")
File "/data2/lidj/venv/StAR/lib/python3.6/site-packages/torch/serialization.py", line 579, in load
with _open_file_like(f, 'rb') as opened_file:
File "/data2/lidj/venv/StAR/lib/python3.6/site-packages/torch/serialization.py", line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/data2/lidj/venv/StAR/lib/python3.6/site-packages/torch/serialization.py", line 211, in init
super(_open_file, self).init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: './data/ctd/new_dev.dict'
However, if i didn't use "--do_eval" in link prediction, it will generate _newdev.dict at last. Do we have any method to generate the _newdev.dict before running link prediction?
Hope you reply. Thanks a lot.