cosin_add_m.prototxt

name: "ArcFace"
layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mirror: true
    mean_value: 127.5
    mean_value: 127.5
    mean_value: 127.5
    scale: 0.0078125
  }
  data_param {
    source: "/home/xia/newwork/lfw/casia_lmdb"
    batch_size: 128
    backend: LMDB
  }
}
############## CNN Architecture ###############
layer {
  name: "conv1_1"
  type: "Convolution"
  bottom: "data"
  top: "conv1_1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    kernel_size: 3
    stride: 2
    pad: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu1_1"
  type: "PReLU"
  bottom: "conv1_1"
  top: "conv1_1"
}
layer {
  name: "conv1_2"
  type: "Convolution"
  bottom: "conv1_1"
  top: "conv1_2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu1_2"
  type: "PReLU"
  bottom: "conv1_2"
  top: "conv1_2"
}
layer {
  name: "conv1_3"
  type: "Convolution"
  bottom: "conv1_2"
  top: "conv1_3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu1_3"
  type: "PReLU"
  bottom: "conv1_3"
  top: "conv1_3"
}
layer {
  name: "res1_3"
  type: "Eltwise"
  bottom: "conv1_1"
  bottom: "conv1_3"
  top: "res1_3"
  eltwise_param { 
    operation: 1
  }
}
layer {
  name: "conv2_1"
  type: "Convolution"
  bottom: "res1_3"
  top: "conv2_1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_size: 3
    stride: 2
    pad: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu2_1"
  type: "PReLU"
  bottom: "conv2_1"
  top: "conv2_1"
}
layer {
  name: "conv2_2"
  type: "Convolution"
  bottom: "conv2_1"
  top: "conv2_2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu2_2"
  type: "PReLU"
  bottom: "conv2_2"
  top: "conv2_2"
}
layer {
  name: "conv2_3"
  type: "Convolution"
  bottom: "conv2_2"
  top: "conv2_3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu2_3"
  type: "PReLU"
  bottom: "conv2_3"
  top: "conv2_3"
}
layer {
  name: "res2_3"
  type: "Eltwise"
  bottom: "conv2_1"
  bottom: "conv2_3"
  top: "res2_3"
  eltwise_param { 
    operation: 1
  }
}
layer {
  name: "conv2_4"
  type: "Convolution"
  bottom: "res2_3"
  top: "conv2_4"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu2_4"
  type: "PReLU"
  bottom: "conv2_4"
  top: "conv2_4"
}
layer {
  name: "conv2_5"
  type: "Convolution"
  bottom: "conv2_4"
  top: "conv2_5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu2_5"
  type: "PReLU"
  bottom: "conv2_5"
  top: "conv2_5"
}
layer {
  name: "res2_5"
  type: "Eltwise"
  bottom: "res2_3"
  bottom: "conv2_5"
  top: "res2_5"
  eltwise_param { 
    operation: 1
  }
}
layer {
  name: "conv3_1"
  type: "Convolution"
  bottom: "res2_5"
  top: "conv3_1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 3
    stride: 2
    pad: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3_1"
  type: "PReLU"
  bottom: "conv3_1"
  top: "conv3_1"
}
layer {
  name: "conv3_2"
  type: "Convolution"
  bottom: "conv3_1"
  top: "conv3_2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3_2"
  type: "PReLU"
  bottom: "conv3_2"
  top: "conv3_2"
}
layer {
  name: "conv3_3"
  type: "Convolution"
  bottom: "conv3_2"
  top: "conv3_3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3_3"
  type: "PReLU"
  bottom: "conv3_3"
  top: "conv3_3"
}
layer {
  name: "res3_3"
  type: "Eltwise"
  bottom: "conv3_1"
  bottom: "conv3_3"
  top: "res3_3"
  eltwise_param { 
    operation: 1
  }
}
layer {
  name: "conv3_4"
  type: "Convolution"
  bottom: "res3_3"
  top: "conv3_4"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3_4"
  type: "PReLU"
  bottom: "conv3_4"
  top: "conv3_4"
}
layer {
  name: "conv3_5"
  type: "Convolution"
  bottom: "conv3_4"
  top: "conv3_5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3_5"
  type: "PReLU"
  bottom: "conv3_5"
  top: "conv3_5"
}
layer {
  name: "res3_5"
  type: "Eltwise"
  bottom: "res3_3"
  bottom: "conv3_5"
  top: "res3_5"
  eltwise_param { 
    operation: 1
  }
}
layer {
  name: "conv3_6"
  type: "Convolution"
  bottom: "res3_5"
  top: "conv3_6"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3_6"
  type: "PReLU"
  bottom: "conv3_6"
  top: "conv3_6"
}
layer {
  name: "conv3_7"
  type: "Convolution"
  bottom: "conv3_6"
  top: "conv3_7"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3_7"
  type: "PReLU"
  bottom: "conv3_7"
  top: "conv3_7"
}
layer {
  name: "res3_7"
  type: "Eltwise"
  bottom: "res3_5"
  bottom: "conv3_7"
  top: "res3_7"
  eltwise_param { 
    operation: 1
  }
}
layer {
  name: "conv3_8"
  type: "Convolution"
  bottom: "res3_7"
  top: "conv3_8"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3_8"
  type: "PReLU"
  bottom: "conv3_8"
  top: "conv3_8"
}
layer {
  name: "conv3_9"
  type: "Convolution"
  bottom: "conv3_8"
  top: "conv3_9"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3_9"
  type: "PReLU"
  bottom: "conv3_9"
  top: "conv3_9"
}
layer {
  name: "res3_9"
  type: "Eltwise"
  bottom: "res3_7"
  bottom: "conv3_9"
  top: "res3_9"
  eltwise_param { 
    operation: 1
  }
}
layer {
  name: "conv4_1"
  type: "Convolution"
  bottom: "res3_9"
  top: "conv4_1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 512
    kernel_size: 3
    stride: 2
    pad: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu4_1"
  type: "PReLU"
  bottom: "conv4_1"
  top: "conv4_1"
}
layer {
  name: "conv4_2"
  type: "Convolution"
  bottom: "conv4_1"
  top: "conv4_2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 512
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu4_2"
  type: "PReLU"
  bottom: "conv4_2"
  top: "conv4_2"
}
layer {
  name: "conv4_3"
  type: "Convolution"
  bottom: "conv4_2"
  top: "conv4_3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 512
    kernel_size: 3
    stride: 1
    pad: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu4_3"
  type: "PReLU"
  bottom: "conv4_3"
  top: "conv4_3"
}
layer {
  name: "res4_3"
  type: "Eltwise"
  bottom: "conv4_1"
  bottom: "conv4_3"
  top: "res4_3"
  eltwise_param { 
    operation: 1
  }
}
layer {
  name: "fc5"
  type: "InnerProduct"
  bottom: "res4_3"
  top: "fc5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 512
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}

layer {
  name: "norm_fc5"
  type: "Normalize"
  bottom: "fc5"
  top: "norm_fc5"
  #top: "feature_norm"
  normalize_param {
    bp_norm: true
  }
}

############### Arc-Softmax Loss ##############

layer {
  name: "fc6"
  type: "InnerProduct"
  bottom: "norm_fc5"
  top: "fc6"
  param {
    lr_mult: 1
  }
  inner_product_param {
    num_output: 10575
    normalize: true
    weight_filler {
      type: "xavier"
    }
    bias_term: false
  }
}

#layer {
#  name: "label_specific_margin"
#  type: "LabelSpecificAdd"
#  bottom: "fc6"
#  bottom: "label"
#  top: "fc6_margin"
#  label_specific_add_param {
#    bias: -0.35
#  }
#}

layer {
  name: "cosin_add_m"
  type: "CosinAddm"
  bottom: "fc6"
  bottom: "label"
  top: "fc6_margin"
  cosin_add_m_param {
    m: 0.5
  }
}

layer {
  name: "fc6_margin_scale"
  type: "Scale"
  bottom: "fc6_margin"
  top: "fc6_margin_scale"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  scale_param {
    filler{
      type: "constant"
      value: 64
    }
  }
}

layer {
  name: "focal_loss"
  type: "FocalLoss"
  bottom: "fc6_margin_scale"
  bottom: "label"
  top: "focal_loss"
  focal_loss_param:{
    type: ORIGIN
    gamma: 2
    alpha: 0.25
    beta: 1
  }
  loss_weight: 1
}

layer {
  name: "accuracy-t"
  type: "Accuracy"
  bottom: "fc6"
  bottom: "label"
  top: "accuracy-t"
  include {
    phase: TRAIN
  }
}

layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "fc6_margin_scale"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TRAIN
  }
}