-
Notifications
You must be signed in to change notification settings - Fork 90
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
请问源项目中的R50模型要如何转换成caffe模型? #2
Comments
R50模型转换可以看下有没有不支持的层,如果有的话可能不能直接转。需要自己写模型转换工具。 |
@clancylian 我转出来,在caffe上跑,结果不一样,面部框变大了,而且5个关键点也不准确。你转出来的结果和官方一样嘛? |
@xiakj @clancylian |
resnet50的转换方法参考:https://github.com/szad670401/advanced-mxnet2caffe |
@OPPOA113 现在检测结果正确了,一定要保证测试图像比例不要发生变化,可以通过调整*_deploy.prototxt中的data层的dims参数解决,也可以在源码中设置。 |
@xiakj 谢谢您。 |
|
@xiakj @clancylian |
@OPPOA113 不太了解,感觉RestNet50模型本身的问题吧,你再好好读读RestNet50的prototxt |
@xiakj |
@OPPOA113 请查收 |
@xiakj 谢谢,已收到。 |
@nuanxinqing 您可以试一下github.com/szad670401/advanced-mxnet2caffe,我是用这个转换出来的。但是caffemodel转换过程中也遇到了一些问题,您留意一下,也可以再沟通。 |
这里 https://github.com/cholihao/Retinaface-caffe 找到了一个google drive链接, 里面有caffe的模型: https://drive.google.com/drive/folders/1VoABSiHXiVlRCEryKtf3UG_BW9236UUp |
@jiapinai 已经好了,谢谢您! |
No description provided.
The text was updated successfully, but these errors were encountered: