Open tomriddle54 opened 5 years ago
Why is 3 different P / R / O networks required?
You can try to combine these 3 networks into 1 cfg-file.
But there is no layer for Facial landmark localization
, so as I understand you should implement it by yourself.
I don't know c well but python I know so how can I create layer can you help lets create a face detection on darknet I feel that we can get about 40 fps face detection on 4gb gpu
Hello again @AlexeyAB I am planning to integrate
mtcnn(Multi-task Cascaded Convolutional Network)
in darknet. The MTCNN model consists of 3 separate networks: the P-Net, the R-Net, and the O-Net: So my question is can i create a cfg file for this and train my model on it. I think it is possible in darknet