Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

prediction on new dataset #43

Closed
Ria312 opened this issue Apr 30, 2021 · 1 comment
Closed

prediction on new dataset #43

Ria312 opened this issue Apr 30, 2021 · 1 comment

Comments

@Ria312
Copy link

Ria312 commented Apr 30, 2021

Hi
How to use this model for the prediction of labels on a new dataset?

Here is the command I am using :

python run_bluebert_ner.py --do_prepare=false --do_train=false --do_eval=false --do_predict=true --task_name="bc5cdr" --vocab_file=vocab.txt --bert_config_file=bert_config.json --init_checkpoint=model.ckpt-1516 --num_train_epochs=1.0 --do_lower_case=False --data_dir=no_label_dataset --output_dir=no_label_output/

I am just keeping "do_predict" true because I want to see the labels the model "model.ckpt-1516" predict after fine-tuning.

Here is the sample data without tags:

oxacalcitriol
suppresses
secondary
hyperparathyroidism
without
inducing
low
bone
turnover
in
dogs
with
renal
failure

Is it necessary to have labels on new dataset as well?

Thanks

@Ria312
Copy link
Author

Ria312 commented May 10, 2021

discovered how to do this.

@Ria312 Ria312 closed this as completed May 10, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant