I wonder why the bbox_pre layer's num_output is always 8

[Peng-wei-Yu]

In the train.prototxt, show as follow:
layer {
name: "bbox_pred"
type: "InnerProduct"
bottom: "data"
top: "bbox_pred"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
inner_product_param {
num_output: 8
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}
I don't understand why the num_output is 8

[zhaoweicai]

It is class-agnostic regression, the output dim = 2*4.

[Peng-wei-Yu]

@zhaoweicai I search the C++ code and see what does is mean, but why class-agnostic regression. Will is be much more robust?