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

作者您好,我想使用50%的数据量测试模型的mAP,该如何设置呢? #46

Closed
coldlarry opened this issue Oct 15, 2021 · 4 comments
Labels
good first issue Good for newcomers

Comments

@coldlarry
Copy link

作者您好,非常感谢您的工作。您使用20%的数据量在VOC上达到了不错的效果,如果我想测试50%的数据量是否可以达到100%数据量的效果,我该怎么修改程序呢?

我粗略看了下代码,是不是只需要增加circle的值就可以了呢?

麻烦您回复下我~

@yuantn
Copy link
Owner

yuantn commented Oct 15, 2021

你好,你可以通过修改 configs/MIAOD.py 中的初始已标注集大小 X_L_0_size 、每一个循环增加的已标注样本数量 X_S_size 和循环数 cycles 来达到你想要的效果。最后一个循环使用的已标注样本数据量等于 X_L_0_size + X_S_size * (len(cycles) - 1)


Hello, you can modify the size of initial labeled set X_L_0_size, the number of added labeled samples after each cycle X_S_size and the number of cycles cycles in configs/MIAOD.py to achieve the effect you want. The amount of labeled data in the last cycle is X_L_0_size + X_S_size * (len(cycles)-1).

@coldlarry
Copy link
Author

感谢!这回答对我帮助很大。

@yuantn yuantn added the good first issue Good for newcomers label Oct 15, 2021
@coldlarry
Copy link
Author

您好作者,为什么你论文里说到先最大化示例不确定性,再最小化示例不确定性。为什么在代码里?这个顺序反而反过来了?

@yuantn
Copy link
Owner

yuantn commented Oct 15, 2021

您好,关于这个问题,请参考问题 #4


Hello, for this question, please refer to Issue #4 .

@yuantn yuantn closed this as completed Nov 15, 2021
yuantn added a commit that referenced this issue Apr 21, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
good first issue Good for newcomers
Projects
None yet
Development

No branches or pull requests

2 participants