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

请教用DBN做一维数据预测 #17

Open
Coder-XWJ opened this issue Jun 29, 2019 · 4 comments
Open

请教用DBN做一维数据预测 #17

Coder-XWJ opened this issue Jun 29, 2019 · 4 comments

Comments

@Coder-XWJ
Copy link

您好,首先感谢您提供的代码。我想要用DBN处理一个Excel表的数据,4000行14列,每行数据是一个单元,需要根据每行14个数据输出0或1,请问x_dim,y_dim和p_dim怎么设啊?因为这个跟mnist是不一样的,代码封装得厉害,也不太清楚一维数据这时候还需不需要p_dim,求告知。

@zhuofupan
Copy link
Owner

应该可以支持一维,我写了支持一维的。你试试。

@Coder-XWJ
Copy link
Author

作者您好,我在用DBN预测BMS的demo预测自己的数据集时(shape=[4000,14]),修改batch_size=100,训练可以运行,但是到了微调的时候报错,Cannot feed value of shape (100,) for Tensor 'DBN/Placeholder_1:0', which has shape '(?, 4000)',我看了下不是很懂self.input_data = tf.placeholder(tf.float32, [None, self.struct[0]])这样设置输入占位符的原因,还有struct为啥那样设置也不太懂,能帮忙解释一下吗?

@zhuofupan
Copy link
Owner

zhuofupan commented Jun 30, 2019 via email

@LovelearnBO
Copy link

您好,首先感谢您提供的代码。我想要用DBN处理一个Excel表的数据,4000行14列,每行数据是一个单元,需要根据每行14个数据输出0或1,请问x_dim,y_dim和p_dim怎么设啊?因为这个跟mnist是不一样的,代码封装得厉害,也不太清楚一维数据这时候还需不需要p_dim,求告知。

你好,请问你最后用DBN处理一维数据成功了嘛~

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

3 participants