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

如果有训练好的模型,作者您提供的代码能把某一层的特征提取出来吗?具体应该如何操作呢? #2

Open
GengCauWong opened this issue Oct 10, 2015 · 7 comments

Comments

@GengCauWong
Copy link

No description provided.

@shicai
Copy link
Owner

shicai commented Oct 10, 2015

仔细阅读 https://github.com/shicai/Caffe_Manual/blob/master/get_features.cpp
或者第一个issue,都有提到

@GengCauWong
Copy link
Author

您好,我主要是在linux下编译的时候总出错误,貌似问题出在protobuf上,麻烦您能说一下在linux下编译的步骤么?

@shicai
Copy link
Owner

shicai commented Oct 12, 2015

@xxlylf 是编译caffe出错,还是编译get_feature出错?如果是后者,请贴上错误信息,如果是前者,请到caffe的issue下找答案

@GengCauWong
Copy link
Author

2015-10-13 09 20 47
请您帮我看一下,我这个编译有问题

@shicai
Copy link
Owner

shicai commented Oct 13, 2015

这个文件依赖于caffe,你单独编译是编不出来的。。。
你把get_features.cpp放在caffe的tools目录下,然后make一次caffe就可以了

@Coldmooon
Copy link

我写了一个在 Xcode 里编译这个 repository 的方法,这样就可以进行单步调试了。 对于 Linux 下的 eclipse, 同样的思路也应该适用。
http://coldmooon.github.io/2015/08/14/compile_caffe_cpp/

@GengCauWong
Copy link
Author

您好,我现在可以成功提取特征了,用caffenet这个模型实验的,但是我自己训练的模型没有成功,错误提示应该是网络配置文件出了问题,您能帮我看看我哪里写的不对么?或者是在您代码的基础上我需要做什么改动2015-10-16 17 07 29

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