Question about the implementation of FCN(heatmap)

layumi / 2015_Face_Detection

CVPR2015 Cascade CNNs for Face Detection

Other

136 stars 70 forks source link

Question about the implementation of FCN(heatmap) #15

Open Seanlinx opened 8 years ago

Seanlinx commented 8 years ago

Hi, layumi, I am interested in the FCN method you adopt in 12-net as you mentioned in the technical report, but I get a little confused about the implementation. Could you please explain the point of deleting first col(row) of resized image in 12-net in scanpic_aflw_fast_slide.m? And why there isn't a subsequent 12-net-c?

Thanks!

layumi commented 8 years ago

@Seanlinx

1.Because there is a stride 2 function in the net, it will skip some image and get a 1/4 small heatmap. So I make up this loss by running code four time to get a whole heatmap.

2.12netc input is the output from 12net. So I didn't use heatmap method in 12net.