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

模型训练时使用的增强策略,参数和论文中的不一样 #9

Closed
gfzwytc opened this issue Jul 16, 2022 · 2 comments
Closed

Comments

@gfzwytc
Copy link

gfzwytc commented Jul 16, 2022

感谢作者的伟大贡献,我在detectron2环境下训练了自己的数据集,训练时输出了使用的增强策略,发现和论文中的表9的增强策略有些不一样,这是为什么呢?
{'zoom_out': {'prob': 0.30000000000000004, 'level': 9}, 'zoom_in': {'prob': 0.25, 'level': 3}}
{'policies':
[[('Color', 0.4, 2), ('translateX', 0.4, 4)],
[('Brightness', 0.2, 4), ('rotate', 0.4, 2)],
[('Sharpness', 0.4, 2), ('shearX', 0.2, 6)],
[('SolarizeAdd', 0.2, 2), ('hflip', 0.5, 1)],
[('Color', 0.0, 8), ('translateY', 0.2, 8)]],
'scale_ratios': {'area': [7, 5, 1], 'prob': [3, 3, 3]}}
论文中的表9的增强策略
image

@gfzwytc gfzwytc changed the title 模型训练完后,如何显示搜索到的增强策略呢 模型训练时使用的增强策略,参数和论文中的不一样 Jul 18, 2022
@yukang2017
Copy link
Member

你好,我当时应该是进来了多次搜索,搜索到的结果会有所波动。两个策略其实差别非常小,我开源的时候找了个稳定性比较好的开源了。您也可以考虑改回文章中的那个,效果差不多的。

@gfzwytc
Copy link
Author

gfzwytc commented Jul 20, 2022

你好,我当时应该是进来了多次搜索,搜索到的结果会有所波动。两个策略其实差别非常小,我开源的时候找了个稳定性比较好的开源了。您也可以考虑改回文章中的那个,效果差不多的。

@gfzwytc gfzwytc closed this as completed Jul 20, 2022
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

2 participants