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

对lib下make测试demo的疑问 #32

Open
JDwu1120 opened this issue May 24, 2018 · 2 comments
Open

对lib下make测试demo的疑问 #32

JDwu1120 opened this issue May 24, 2018 · 2 comments

Comments

@JDwu1120
Copy link

您好,我是一名本科的学生,最近在研究rcnn这方面的东西,我之前已经使用过caffe训练过cnn的模型,目前想clone您的代码学习一下rcnn,因为之前训练都是在Intel的devcloud上进行的,所以在本地都是用CPU训练一些小的数据集(本人机器为mac),所以我想问一下您们README上的demo是一定要在支持CUDA驱动的gpu环境的才能运行吗?因为我在mac运行(有CUDA环境但不支持NVDIA的gpu驱动)会报错。
报错信息如下:
nms/gpu_nms.cpp:2074:3: error: no matching function for call to '_nms'
_nms((&(*__Pyx_BufPtrStrided1d(__pyx_t_5numpy_int32_t *, __pyx_pybuffernd_keep.rcbuffer->pybuffer.buf, __pyx_t_10, __pyx_pybuffernd_keep.diminfo[0].strides))), (&__pyx_v_num_out), (&(...
^~~~
nms/gpu_nms.hpp:1:6: note: candidate function not viable: no known conversion from '__pyx_t_5numpy_int32_t ' (aka 'long ') to 'int ' for 1st argument
void _nms(int
keep_out, int
num_out, const float
boxes_host, int boxes_num,

看上去像是gpu驱动的问题。
所以我想请教您,是不是你们测试的demo只能在支持CUDA的gpu环境下才能make成功?
万分感谢。

@mjq11302010044
Copy link
Owner

mjq11302010044 commented May 24, 2018

是的,一般是需要CUDA支持的,在NMS步骤上

@JDwu1120
Copy link
Author

好的。谢谢!

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