search

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

scans location recover in function about generateBoundingBox() ? #27

Open Wenchao-Du opened 6 years ago

Wenchao-Du commented 6 years ago

i have been reimplementing this work presently, but i have a problem about the "P-net"，we need recover original scans location from output feature maps, but why the stride was set 2, i could not understand it clearly, the code is follow: stride=2; boundingbox=[fix((stride*(boundingbox-1)+1)/scale) fix((stride*(boundingbox-1)+cellsize-1+1)/scale) score reg]; could you explain it simplely? thanks.

ZhiqiJiang commented 5 years ago

Because P-net only have one pooling layer, namely shifting one step in output feature map is equal to shifting two step in input layer.