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

我用自己的数据集,训练了100个epoch,但是训练输出的结果Precision, Recall, F1 Score三个参数为什么会出现大于1的现象,这不科学,没有找到是什么原因,求解答 #50

Open
mortonhan opened this issue Jun 1, 2023 · 4 comments

Comments

@mortonhan
Copy link

image

@Fafa-DL
Copy link
Owner

Fafa-DL commented Jun 2, 2023

训练什么模型出现的该情况?再跑一遍问题可否复现?尽量贴出终端信息方便溯源

@mortonhan
Copy link
Author

image
image
image

训练的resnet50模型,我自己修改了一下bitchsize=32和学习率。其他的未做修改,第一遍跑了50epoch输出的csv中Precision, recall, F1 score均出现了大于1的现象,第二遍跑了 300 epoch中途也出现了大于1的现象,但是并没有报错

@Fafa-DL
Copy link
Owner

Fafa-DL commented Jun 3, 2023

我用示例花卉数据集跑了多次,未出现这种情况,建议你跑跑其他如花卉等数据集看是否会出现该情况,先debug是code问题还是数据集问题;若未出现大于1情况,可以看看是否测试集哪里不对。影响准召率的只有GT与Pre
https://github.com/Fafa-DL/Awesome-Backbones/blob/b99083e8c5099604c95af0ccb9ea5cadfa7f7bd7/core/evaluations/eval_metrics.py#L96C1-L115

@shiniaaaaa
Copy link

我训练VGG16也出现了Precision, recall, F1 score大于1的情况,不知道怎么回事

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