search

onehaitao / Att-BLSTM-relation-extraction

Implementation of Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification.
MIT License
76 stars 17 forks source link

I run the code and get the F1 score 82.73 #5

Closed songhanyu closed 3 years ago

songhanyu commented 3 years ago

Hi, thanks for your code!I have a question,can you give me some advice? I run your code,but only get F1 score 82.73,never get 83.13 in your log file.If you have time, thanks for your advice.

onehaitao commented 3 years ago

You can check your version of Pytorch and CUDA. As far as I know, different versions lead to different results.

songhanyu commented 3 years ago

Thank you very much! I use Pytorch of v1.5.0, because I cannot get your 1.3.0 Pytorch(you write on the README page) on the official site https://pytorch.org/get-started/previous-versions/ .Can you tell me your version of Pytorch and CUDA, thanks again!!And it's so kind of you!

onehaitao commented 3 years ago

You can run the following commands: pip install torch==1.3.0+cu92 -f https://download.pytorch.org/whl/torch_stable.html

songhanyu commented 3 years ago

Thanks very much! 

---Original--- From: "HT @.> Date: Fri, May 7, 2021 21:38 PM To: @.>; Cc: @.**@.>; Subject: Re: [onehaitao/Att-BLSTM-relation-extraction] I run the code and get the F1 score 82.73 (#5)

You can run the following commands: pip install torch==1.3.0+cu92 -f https://download.pytorch.org/whl/torch_stable.html

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.