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

我使用仓库提供的bird预训练模型在2080ti*2 torch0.4.1 cuda9.2平台运行得到的refine acc是89.023,我自己用这个平台训练结果是88.989,和你说的89.3存在一定差距 #13

Open
17314796423 opened this issue May 30, 2024 · 0 comments

Comments

@17314796423
Copy link

image
image
代码改动

  • 只是把attention_crop_drop换成了你提供的attention_crop_drop2,因为mask在cpu上,
  • correct[:k].contiguous().view(-1).float().sum(0, keepdim=True)是utils.py里面的

只是想确认一下提供在onedrive上的模型是不是在你的平台上时89.30,如果排除是平台问题,
我就可以在你的代码上重新实现基于WS-DAN的另一篇paper了https://github.com/aioz-ai/SAC
他也是用的WS-DAN的tf代码基础上加的内容

@17314796423 17314796423 changed the title 我使用仓库提供的bird预训练模型在2080ti torch0.4.1 cuda9.2平台运行得到的refine acc是89.023,我自己用这个平台训练结果是88.989,和你说的89.3存在一定差距 我使用仓库提供的bird预训练模型在2080ti*2 torch0.4.1 cuda9.2平台运行得到的refine acc是89.023,我自己用这个平台训练结果是88.989,和你说的89.3存在一定差距 May 30, 2024
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

1 participant