Closed sidgan closed 6 years ago
@sidgan Hi! I have the same question with you! Did you figure out this problem? Thanks.
Pnet is a full conv network, it doesn't matter what size the input is. Its output rely on its input size. just not smaller than 12x12. @sidgan @Lisupy
Hi, Im trying to follow through the code and understand how mtcnn works. I understand that for each image, for each scale the detection comes from each of the networks. In particular I am talking about the Pnet right now.
The image is rescaled according to the scales produced earlier and the rescaled image goes into the Pnet as follows in the code:
For reference I have printed out the original size and the rescaled size: ORIGINAL Height: 340 ORIGINAL Width: 151 SCALE USED (were computed before): 0.107493555074 RESCALED Height: 37 RESCALED Width: 17
The net corresponds to Pnet and in det1.prototxt (PNet) the input size should have h=12 and w=12.
What I don't understand is where is the size going from size of image to 12x12?