Why the output of "rfcn_bbox" layer is 392?

[panovr]

In file train_agnostic.prototxt line 3759:

layer {
    bottom: "conv_new_1"
    top: "rfcn_bbox"
    name: "rfcn_bbox"
    type: "Convolution"
    convolution_param {
        num_output: 392 #8*(7^2) cls_num*(score_maps_size^2)
        kernel_size: 1
        pad: 0
        weight_filler {
            type: "gaussian"
            std: 0.01
        }
        bias_filler {
            type: "constant"
            value: 0
        }
    }
    param {
        lr_mult: 1.0
    }
    param {
        lr_mult: 2.0
    }
}

The output number is 392. The comment says that 392 equals cls_num*(score_map_size^2). However, why cls_num is 8? I think this should be 2*4*(score_map_size^2).

[liyi14]

You are right. We will fix it.