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

generator的loss一直上升，discriminator的loss一直下降 #33

Open
iloveOREO opened this issue May 19, 2020 · 2 comments
Open

generator的loss一直上升，discriminator的loss一直下降 #33

iloveOREO opened this issue May 19, 2020 · 2 comments

Comments

@iloveOREO
Copy link

在自己的数据集上训练，G网络和D网络没有明显的对抗关系，试着调整了一下学习率，除了D网络最开始收敛的慢了一些，但是D开始loss下降就不回头了。。。看起来像是学到了G网络没有察觉的特征，然后G网络的loss就不断上升，请问怎么让G网络和D网络具有明显的对抗关系，或者什么样的训练曲线才是比较理想的GAN网络训练结果呢？
@Adorablepet
Copy link

@iloveOREO 我想问下你的数据集是怎么做的标签，按照LRW的格式吗？还是？

@iloveOREO
Copy link
Author

@iloveOREO 我想问下你的数据集是怎么做的标签，按照LRW的格式吗？还是？

我的关键点是百度人脸检测得到的

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
@iloveOREO @Adorablepet