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

请教个问题 cnn_minist.py里面 #2

Open
yuncliu opened this issue Jul 15, 2016 · 1 comment
Open

请教个问题 cnn_minist.py里面 #2

yuncliu opened this issue Jul 15, 2016 · 1 comment

Comments

@yuncliu
Copy link

yuncliu commented Jul 15, 2016

w_conv1 = weight_variable([5, 5, 1, 32])
这里这个shape最后一个为什么是32呢, 这个有没有啥说法,我理解是把一张图片分成32张,每张可能提取到不同的特征。 我把32换成1, 后面的64换成2,也能运行,而且训练速度更快,迭代到最后正确率差不多

@wlmnzf
Copy link
Owner

wlmnzf commented Dec 28, 2016

不好意思,之前匆匆跑去准备考研,就没再继续,根据官方文档描述,这个卷积的权重张量形状是[5, 5, 1, 32],前两个维度是patch的大小,接着是输入的通道数目,最后是输出的通道数目

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