search

YuvalNirkin / face_segmentation

Deep face segmentation in extremely hard conditions
Apache License 2.0
730 stars 151 forks source link

Network Output #15

Closed mfournarakis closed 5 years ago

mfournarakis commented 5 years ago

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

YuvalNirkin commented 5 years ago

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.