# Assumes a BGR image from which the mean pixel value has been subtracted
# We used B=104, G=117, R=123 in our experiments.

input: "im_concat"
input_dim: 1
input_dim: 3
input_dim: 227
input_dim: 227

layer {
  name: "conv1"
  type: "Convolution"
  bottom: "im_concat"
  top: "conv1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    kernel_size: 11
    stride: 4
    
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}

layer {
  name: "bn1"
  type: "BatchNorm"
  bottom: "conv1"
  top: "bn1"

  param {
    lr_mult: 0
  }
  param {
    lr_mult: 0
  }
  param {
    lr_mult: 0
  }
}

layer {
  name: "relu1"
  type: "ReLU"
  bottom: "bn1"
  top: "bn1"
}

layer {
  name: "pool1"
  type: "Pooling"
  bottom: "bn1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}

layer {
  name: "norm1"
  type: "LRN"
  bottom: "pool1"
  top: "norm1"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}

layer {
  name: "conv2"
  type: "Convolution"
  bottom: "norm1"
  top: "conv2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 5
    
    group : 2
    pad : 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1.0
    }
  }
}

layer {
  name: "bn2"
  type: "BatchNorm"
  bottom: "conv2"
  top: "bn2"

  param {
    lr_mult: 0
  }
  param {
    lr_mult: 0
  }
  param {
    lr_mult: 0
  }
}

layer {
  name: "relu2"
  type: "ReLU"
  bottom: "bn2"
  top: "bn2"
}

layer {
  name: "pool2"
  type: "Pooling"
  bottom: "bn2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}

layer {
  name: "norm2"
  type: "LRN"
  bottom: "pool2"
  top: "norm2"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}

layer {
  name: "conv3"
  type: "Convolution"
  bottom: "norm2"
  top: "conv3"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0
  }
  convolution_param {
    num_output: 384
    kernel_size: 3
    pad : 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}

layer {
  name: "bn3"
  type: "BatchNorm"
  bottom: "conv3"
  top: "bn3"

  param {
    lr_mult: 0
  }
  param {
    lr_mult: 0
  }
  param {
    lr_mult: 0
  }
}

layer {
  name: "relu3"
  type: "ReLU"
  bottom: "bn3"
  top: "bn3"
}

layer {
  name: "conv4"
  type: "Convolution"
  bottom: "bn3"
  top: "conv4"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0
  }
  convolution_param {
    num_output: 384
    kernel_size: 3
    
    group : 2
    pad : 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1.0
    }
  }
}

layer {
  name: "bn4"
  type: "BatchNorm"
  bottom: "conv4"
  top: "bn4"

  param {
    lr_mult: 0
  }
  param {
    lr_mult: 0
  }
  param {
    lr_mult: 0
  }
}

layer {
  name: "relu4"
  type: "ReLU"
  bottom: "bn4"
  top: "bn4"
}

layer {
  name: "conv5"
  type: "Convolution"
  bottom: "bn4"
  top: "conv5"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_size: 3
    
    group : 2
    pad : 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1.0
    }
  }
}

layer {
  name: "bn5"
  type: "BatchNorm"
  bottom: "conv5"
  top: "bn5"

  param {
    lr_mult: 0
  }
  param {
    lr_mult: 0
  }
  param {
    lr_mult: 0
  }
}

layer {
  name: "relu5"
  type: "ReLU"
  bottom: "bn5"
  top: "bn5"
}

layer {
  name: "pool5"
  type: "Pooling"
  bottom: "bn5"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}

layer {
  name: "fc6"
  type: "InnerProduct"
  bottom: "pool5"
  top: "fc6"
  param {
    lr_mult: 1.0
    decay_mult: 1
  }
  param {
    lr_mult: 2.0
    decay_mult: 0
  }
  inner_product_param {
    num_output: 4096

    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1.0
      }
    }
}

layer {
  name: "relu6"
  type: "ReLU"
  bottom: "fc6"
  top: "fc6"
}

layer {
  name: "drop6"
  type: "Dropout"
  bottom: "fc6"
  top: "fc6"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc7"
  type: "InnerProduct"
  bottom: "fc6"
  top: "fc7"
  param {
    lr_mult: 1.0
    decay_mult: 1
  }
  param {
    lr_mult: 2.0
    decay_mult: 0
  }
  inner_product_param {
    num_output: 4096
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1.0
    }
  }
}

layer {
  name: "relu7"
  type: "ReLU"
  bottom: "fc7"
  top: "fc7"
}

layer {
  name: "drop7"
  type: "Dropout"
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}


layer {
  name: "predict_"
  type: "InnerProduct"
  bottom: "fc7"
  top: "predict_"
  param {
    lr_mult: 1.0
    decay_mult: 1
  }
  param {
    lr_mult: 2.0
    decay_mult: 0
  }
  inner_product_param {
    num_output: 30
    axis: 1
#    axis: 2
      
   weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}