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

EPE和D1非常小 在自己数据集上训练过拟合？ #42

Open
guangxuwang opened this issue Oct 19, 2023 · 3 comments
Open

EPE和D1非常小 在自己数据集上训练过拟合？ #42

guangxuwang opened this issue Oct 19, 2023 · 3 comments

Comments

@guangxuwang
Copy link

guangxuwang commented Oct 19, 2023 •
edited

EPE和D1非常小 @@@@在自己数据集上训练，是过拟合了吗？

image
@gangweiX
Copy link
Owner

嗨，你这个是什么数据集呢，有没有训练loss曲线，可以观察一下训练loss是否下降，如果能正常下降，就还可以

@guangxuwang
Copy link
Author

guangxuwang commented Oct 21, 2023 •
edited

嗨，你这个是什么数据集呢，有没有训练loss曲线，可以观察一下训练loss是否下降，如果能正常下降，就还可以

博主感谢回复，这个是我自己渲染的数据集，epe和live_loss 都下降。数据集和训练损失如下：

image
image

@gangweiX
Copy link
Owner

那看着是比较正常的，是视差分布范围太小了吗？还是显示的时候有什么倍数原因呢？又或者你这个数据集比较简单，效果很好？可以在测试集上测试一下，如果效果很好，那就没有问题

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
@gangweiX @guangxuwang