icylord
commented
9 years ago You can use C/C++ to implement it.
Open weiyt2014 opened 9 years ago
icylord
commented
9 years ago You can use C/C++ to implement it.
jwyang
commented
9 years ago Yes, you are right. I have implemented the testing codes using C++, which is a simple transformation from Matlab codes. :)
ÔÚ 2014-11-05 20:39:14£¬"ShengyinWu" notifications@github.com дµÀ£º
You can use C/C++ to implement it.
¡ª Reply to this email directly or view it on GitHub.
twyt
commented
9 years ago How much time consume respectively on c++/c and matlab and how many imgs used ?
jwyang
commented
9 years ago in my laptop, it comsumes less than 1ms on c++ and a dozens of ms using matlab
发自nubia手机
twyt notifications@github.com编写：
How much time consume respectively on c++/c and matlab and how many imgs used ?
— Reply to this email directly or view it on GitHub.
weiyt2014
commented
9 years ago I'm sorry to interrupt you again!I hope to know whether you train to get LBFRegModel? My result isn't good! If you obtain a LBFRegModel, can I use it to test it ?
在 2014-12-03 06:02:21，"jwyang" notifications@github.com 写道： in my laptop, it comsumes less than 1ms on c++ and a dozens of ms using matlab
发自nubia手机
twyt notifications@github.com编写：
How much time consume respectively on c++/c and matlab and how many imgs used ?
— Reply to this email directly or view it on GitHub.
— Reply to this email directly or view it on GitHub.
weiyt2014
commented
9 years ago I'm sorry to interrupt again! I found "Data{i}.bbox_gt" is used in loadsample.m,test.m,globalpredicition.m, but it is obtained by 68 landmarks from .pts file.If I don't have .pts file,how can I get it? What's more, I hope to know meanshape_resize in test.m and it's used by LBFRegmodel of training model? What is it used? Thanks very much!
在 2014-12-03 06:02:21，"jwyang" notifications@github.com 写道： in my laptop, it comsumes less than 1ms on c++ and a dozens of ms using matlab
发自nubia手机
twyt notifications@github.com编写：
How much time consume respectively on c++/c and matlab and how many imgs used ?
— Reply to this email directly or view it on GitHub.
— Reply to this email directly or view it on GitHub.
jwyang
commented
9 years ago You can obtain the bbox_gt using any face detector as you like.
the mean_shape originially is in range [0, 1; 0, 1], we need to rescale it to adapt to the current face region.
On Wed, Dec 3, 2014 at 8:48 PM, weiyt2014 notifications@github.com wrote:
I'm sorry to interrupt again! I found "Data{i}.bbox_gt" is used in loadsample.m,test.m,globalpredicition.m, but it is obtained by 68 landmarks from .pts file.If I don't have .pts file,how can I get it? What's more, I hope to know meanshape_resize in test.m and it's used by LBFRegmodel of training model? What is it used? Thanks very much!
在 2014-12-03 06:02:21，"jwyang" notifications@github.com 写道： in my laptop, it comsumes less than 1ms on c++ and a dozens of ms using matlab
发自nubia手机
twyt notifications@github.com编写：
How much time consume respectively on c++/c and matlab and how many imgs used ?
— Reply to this email directly or view it on GitHub.
— Reply to this email directly or view it on GitHub.
— Reply to this email directly or view it on GitHub https://github.com/jwyang/face-alignment/issues/5#issuecomment-65529962.
Jianwei Yang Beijing University of Posts and Telecommunications Institute of Automation, Chinese Academy of Sciences 14th floor in Intelligence Building 95 Zhongguancun East Road Haidian District, Beijing 100190, China
杨健伟 北京邮电大学 中国科学院自动化研究所 北京海淀区中关村东路95号智能化大厦14层 邮政编码：100190
3000FPS is mentioned in the paper.But I run the code to test the efficient.The code deal with 224 images needing 5 minuters.I feel the efficient cann't meet our need.I feel training random forest need a long time.But I don't know how to improve it. What's more, the code run needs what conditions to the hardware? Meanwhile, I hope you can give me some directions. Thanks very much!