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.

Sign up for GitHub

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

Jump to bottom

oneshot finetune 的迭代次数 #7

Open
muximuxi opened this issue Feb 16, 2023 · 4 comments
Open

oneshot finetune 的迭代次数 #7

muximuxi opened this issue Feb 16, 2023 · 4 comments

Comments

@muximuxi
Copy link

请问，oneshot的时候，大概跑多少个epoch会有比价好的效果？
@williamyang1991
Copy link
Owner

代码里给的即是推荐的epoch数，为20*1=20个epoch

TET-GAN/src/options.py

Lines 66 to 67 in bdfca14

self.parser.add_argument('--outer_iter', type=int, default=20, help='number of iteration for fading in progressive training')
self.parser.add_argument('--epoch', type=int, default=1, help='number of epoch for each outer iteration')

@muximuxi
Copy link
Author

嗯 谢谢！试下来是默认的结果比较好，但是无法达到预训练模型中给定风格出来的效果。是不是自己的数据重新训练一下比较好？

@williamyang1991
Copy link
Owner

ont-shot毕竟数据样本太少了，所以效果差一些是很正常的

如果有足够的数据重新训练肯定效果会更好

@muximuxi
Copy link
Author

嗯嗯，好的，谢谢~

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@williamyang1991 @muximuxi