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

关于LOAD_INITIAL和TEST_ONLY #12

Open
User766843 opened this issue Mar 19, 2024 · 2 comments
Open

关于LOAD_INITIAL和TEST_ONLY #12

User766843 opened this issue Mar 19, 2024 · 2 comments

Comments

@User766843
Copy link

您好,感谢您的项目让我受益匪浅。我是一个初学者,现在我有一个困惑:在基线模型DCRNN中,在run_demo_pytorch.py和dcrnn_train_pytorch.py中均有 parser.add_argument('--LOAD_INITIAL', default=False, type=bool, help='If LOAD_INITIAL.')
parser.add_argument('--TEST_ONLY', default=False, type=bool, help='If TEST_ONLY.')这两行代码,那么什么时候需要设置LOAD_INITIAL为True,什么时候需要设置TEST_ONLY为True呢?希望您能够解答。

@zouguojian
Copy link
Owner

您好,感谢您的项目让我受益匪浅。我是一个初学者,现在我有一个困惑:在基线模型DCRNN中,在run_demo_pytorch.py和dcrnn_train_pytorch.py中均有 parser.add_argument('--LOAD_INITIAL', default=False, type=bool, help='If LOAD_INITIAL.') parser.add_argument('--TEST_ONLY', default=False, type=bool, help='If TEST_ONLY.')这两行代码,那么什么时候需要设置LOAD_INITIAL为True,什么时候需要设置TEST_ONLY为True呢?希望您能够解答。

我用英文回答你,防止有的外国学术人也遇到这个问题哈。谢谢你的问题。 DCRNN 已在我们的存储库中复现,但请记住 run_demo_pytorch.py 用于直接测试项目,dcrnn_train_pytorch.py 用于训练模型。 这意味着当您换为其他数据集时,某些独特因素(例如 LOAD_INITIAL)不会更改。你只需要更改跟数据集相关的参数就可以。
Thank you for your question. The DCRNN has been reproduced in our repository, but please remember that the run_demo_pytorch.py is used to test the project directly, and dcrnn_train_pytorch.py is used to train the model. This means that some unique factors, such as LOAD_INITIAL, are not changed when you change the other datasets. You can change the parameters that are related to your datasets.

@zouguojian
Copy link
Owner

如果还有其他问题,可以根据主页提供的邮箱或者微信联系我都行。也欢迎合作,共同发表文章。祝好,科研顺利。

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