-
Notifications
You must be signed in to change notification settings - Fork 276
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
初始化参数问题 #28
Comments
@CSG1111 |
我是把您的代码放在了我自己代码中,w参数设置0,最后学习到的也是0,所以non-local就相当于不起作用,我的问题是不是因为w参数设置为0的问题,w可以设置成其他初始化类型吗? |
在我的代码中loss是下降的,训练后w最后是0,但是其他参数均不是0。我把他集成到我的检测代码中了 |
如果不设置为0,结果会怎样? 我测试了一下,demo_MNIST.py训练后不是0. 之前我也有可视化过block里面的矩阵,不会存在全0的情况。 可以把代码放出来吗?会不会是optimizer里面没有把block的参数传进去? |
您好,我在您的基础上把图像non-local改到视频上了,感觉怪怪的,您能给看看吗?qq:1357715848 |
@AlexHex7 你好,non-local block的参数初始化你是怎么设置的,我想把它用在视频分类当中,我自己初始化的参数,训练的很糟糕,能说一下你的初始化参数吗?谢谢 |
@CSG1111 请问你解决了吗?我也遇到了W最后全为0的问题。 |
您好,我按照您的方法训练,w初始设置0 ,在训练完成w还是0,这样的话non-local就不起作用了啊,望解答,谢谢。
The text was updated successfully, but these errors were encountered: