about some parameters' settings and what the difference between your BN layer and the one from blvc/caffe?

[zimenglan-sysu-512]

hi @hszhao , why do you set mult_lr so large in the succeed conv layers after conv5_3/relu layer? e.g.

layer {
  name: "conv6"
  type: "Convolution"
  bottom: "conv5_4"
  top: "conv6"
  param {
    lr_mult: 10
    decay_mult: 1
  }
  param {
    lr_mult: 20
    decay_mult: 1
  }
  convolution_param {
    num_output: 21
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "msra"
    }
  }
}

and what the differences between your BN layer and the one from BLVC/caffe ?

thanks.

[hszhao]

Hi, we assume that the newly added layers should have a larger lr then layers that are initialized from pretrained models. For the bn problem, the one in 'BLVC/caffe' does the normalization first then followed by a 'scale' layer to learn the transfer. While the one in this repo merge 'slope' and 'bias' in 'scale' layer into the bn layer. Thanks.