kpzhang93 / MTCNN_face_detection_alignment

Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks
MIT License
2.8k stars 1.01k forks source link

the question about the way to generate train datas #39

Open geoffzhang opened 6 years ago

geoffzhang commented 6 years ago

why is used the pnet to generate train datas for rnet? Whether can I use the same way to gererate train datas in pnet to generate train datas fot rnet?

ilyanelken commented 5 years ago

@geoffzhang Hi, in forward pass RNet input is PNet output, thus the same should happen during training. Ilya

geoffzhang commented 5 years ago

Ok, I see, thanks.