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

whyPrecision,recall,f1=0? #2

Open
GaiGJin opened this issue Dec 8, 2019 · 5 comments
Open

whyPrecision,recall,f1=0? #2

GaiGJin opened this issue Dec 8, 2019 · 5 comments

Comments

@GaiGJin
Copy link

GaiGJin commented Dec 8, 2019

2019-12-08 02:40:16,055 - Causality - INFO - Valid Loss - 0.06650793552398682
2019-12-08 02:40:16,055 - Causality - INFO - Valid Acc - 0.6290983606557377
2019-12-08 02:40:16,056 - Causality - INFO - Valid Precision - 0.0
2019-12-08 02:40:16,056 - Causality - INFO - Valid Recall - 0.0
2019-12-08 02:40:16,056 - Causality - INFO - Valid F1 - 0.0
2019-12-08 02:40:16,056 - Causality - INFO - Valid AUCROC - 0.5475642017744344
2019-12-08 02:40:16,056 - Causality - INFO - Valid AUCPRC - 0.41483413856191564
您好,打扰了,我运行过程中准确率有显示,但是pre,recall都是0,大概是什么原因呢?

@GaiGJin
Copy link
Author

GaiGJin commented Dec 8, 2019

预测标签都是非因果关系。这个大概是哪里有错呢?

@shiningliang
Copy link
Owner

这是哪个数据集和模型的结果?

@GaiGJin
Copy link
Author

GaiGJin commented Dec 12, 2019

altlex_train.tsv训练过程中的输出

@shiningliang
Copy link
Owner

您先设config.py里的self.is_fc=False,再试一下,用focal loss的结果不太稳定

@hechuan11
Copy link

请问运行python torch_run.py run --prepare=True --build=True会报找不到transfer_file文件的错误,提供的数据集里没有2010_random_filtered.json这个文件。我是刚接触深度学习的学生,打扰老师了。

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

3 participants