Closed Edwardmark closed 6 years ago
@kingrain213 不是吧,计算量是一样的
@Edwardmark, PNet does not use fully connected layer, as input of PNet is a image without fixed resolution which allows dynamic input and output resolution while RNet, ONet need fixed size input (24x24x3 and 48x48x3), you may read https://kpzhang93.github.io/MTCNN_face_detection_alignment/index.html matlab codes for details.
@choice17 Thanks man.
只是粗略的计算个结果出来,减少参数和计算量?