Open herleeyandi opened 7 years ago
Hi thank you for your reply @jianchao-li . Could you give us the detail how to train the P-Net, R-Net, and O-Net?, they should train separately right? Also what is the training data format? for example O-Net needs: ROI of face [x1,y1,w,h] and also 5 landmarks (10 element in total). Where can we find the data and do you have any specific suggestion to prepare the data before training all of them? -Thank you-
@herleeyandi have you produce 68 face landmark points successfully?
@herleeyandi did you manage to do it ? i'm in the same stage and looking how to change it to 68pt
Hello I am new in face detection and landmark detection. My question is based on this network how can I produce 68 points of landmark, because in thisdemo it just can produce 5 points. Do I need to train again with 68 landmark? -Thank you-