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

The testing process #2

Open
Weejaa04 opened this issue Nov 4, 2022 · 1 comment
Open

The testing process #2

Weejaa04 opened this issue Nov 4, 2022 · 1 comment

Comments

@Weejaa04
Copy link

Weejaa04 commented Nov 4, 2022

Hi, it is a very interesting paper. However, I have several questions regarding the code in lines 534-578 in file CMFSL_UP_main.py

  1. What is the purpose of doing the test in several episodes (i.e. episodes 1,1000, and 2000)?
  2. Did you report the best test result from those episodes as your testing accuracy? I am confused about this part because as my understanding, we do that kind of procedure for validation data, and then once the learning episode finishes we test the model with the test data.

Thank you

@Dawn-LLL
Copy link

你好 ,我想请教一下,你在实验的过程中使用的源数据是按照论文中的吗? 采用四个数据集作为源数据。

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

2 participants