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

代码,模型都不变,换一张图,点就乱了 #6

Open
fernandot3721 opened this issue Sep 19, 2017 · 4 comments
Open

代码,模型都不变,换一张图,点就乱了 #6

fernandot3721 opened this issue Sep 19, 2017 · 4 comments

Comments

@fernandot3721
Copy link

当然,我将
cv::Point x = cv::Point(int(feat[2 * i] * img.cols), int(feat[2 * i + 1] * img.rows));//这里的278、289是图像的分辨率,我偷懒了
改好了

原本那张图是对的,随便换一张图就错了

result

@panda-lab
Copy link
Owner

@fernandot3721 先用dlib把人脸框找到,然后处理,或者其他的人脸检测算法,效果有可能不如dlib好,我用dlib训练的。

@fernandot3721
Copy link
Author

@lsy17096535 就是说输入图片必须是已经对齐并剪裁过的纯人脸部分,而这个landmark库只会计算landmark,不包含检测对吧?

@panda-lab
Copy link
Owner

panda-lab commented Sep 20, 2017

@fernandot3721 对,输入的人脸必须是人脸框已经标定好的,然后landmark去给他做点的标定。看一下我的 https://github.com/lsy17096535/face-landmark

@Andrawzyf
Copy link

@fernandot3721 先用dlib把人脸框找到,然后处理,或者其他的人脸检测算法,效果有可能不如dlib好,我用dlib训练的。

用Dlib训练的啥?你这个不是caffe的model么?

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