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

111 #10

Open
lhjlhj11 opened this issue Mar 12, 2022 · 7 comments
Open

111 #10

lhjlhj11 opened this issue Mar 12, 2022 · 7 comments

Comments

@lhjlhj11
Copy link

what does the cheb_k mean?Thank you!

@HeMOua
Copy link

HeMOua commented Apr 28, 2022

what does the cheb_k mean?Thank you!

应该是Chebyshev多项式的阶数

@wy123go
Copy link

wy123go commented Dec 6, 2022

what does the cheb_k mean?Thank you!

应该是Chebyshev多项式的阶数

同学,请问一下,你有用03数据集复现该模型吗

@HeMOua
Copy link

HeMOua commented Dec 8, 2022

what does the cheb_k mean?Thank you!

应该是Chebyshev多项式的阶数

同学,请问一下,你有用03数据集复现该模型吗

没,只用了04 07 08

@wy123go
Copy link

wy123go commented Dec 8, 2022

what does the cheb_k mean?Thank you!

应该是Chebyshev多项式的阶数

同学,请问一下,你有用03数据集复现该模型吗

没,只用了04 07 08
好的,感谢你的回复,我用03的,MAPE达到了几十万,也不知道是什么原因

@BellChai
Copy link

what does the cheb_k mean?Thank you!

应该是Chebyshev多项式的阶数

同学,请问一下,你有用03数据集复现该模型吗

没,只用了04 07 08
好的,感谢你的回复,我用03的,MAPE达到了几十万,也不知道是什么原因

应该只是数据集中出现了除0问题。修改一下MAPE的计算就好了:
把metrics.py中的MAPE_torch函数的
return torch.mean(torch.abs(torch.div((true - pred), true)))
改为
mask = true>0.1
return ((pred[mask]-true[mask])/true[mask]).abs().sum()/(mask.sum())
就好了

@lidexf
Copy link

lidexf commented Oct 6, 2024

what does the cheb_k mean?Thank you!

应该是Chebyshev多项式的阶数

同学,请问一下,你有用03数据集复现该模型吗

没,只用了04 07 08
好的,感谢你的回复,我用03的,MAPE达到了几十万,也不知道是什么原因

应该只是数据集中出现了除0问题。修改一下MAPE的计算就好了: 把metrics.py中的MAPE_torch函数的 return torch.mean(torch.abs(torch.div((true - pred), true))) 改为 mask = true>0.1 return ((pred[mask]-true[mask])/true[mask]).abs().sum()/(mask.sum()) 就好了

忽略掉真实值小于等于0.1,这样合理吗?

@lidexf
Copy link

lidexf commented Oct 7, 2024

论文中,使用的切比雪夫多项式K=2,可是
for k in range(2, self.cheb_k):
support_set.append(torch.matmul(2 * supports, support_set[-1]) - support_set[-2])这里循环时要求至少等于3

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

5 participants