why the bbox_targets has 8 dim not 4?

daijifeng001 / R-FCN

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Other

1.25k stars 543 forks source link

why the bbox_targets has 8 dim not 4? #30

Closed vzvzx closed 8 years ago

vzvzx commented 8 years ago

why the bbox_targets have 8 dim, not 4? and the begin 4 dim is all 0?

daijifeng001 commented 8 years ago

The first 4 dims are for the null category, and is not used.

hongjo commented 7 years ago

The two classes-background and foreground-exist in the layer of class agnostic bbox regression. As mentioned by @daijifeng001, the background class is actually not used.