YuvalNirkin / face_segmentation

Deep face segmentation in extremely hard conditions

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Network Output

mfournarakis opened this issue · comments

I'm trying to understand the output of the caffe network and where argmax prediction is coming from in the python interface: out = net.blobs['score'].data[0].argmax(axis=0)

The output: net.blobs['score'].data has 21 channels. What are the additional 20 channels and how do we know that if a face pixel is present, the maximum value will be in the second channel?

Thanks

Exactly, the maximum value will be in the second channel for face pixels.

The other 19 channels are not used and were removed in the new model for the 300X300 resolution.