RankingCNN updated to new version of Caffe

RankingCNNUpdated.prototxt

name: "CaffeNet"
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param { shape: { dim: 1 dim: 3 dim: 227 dim: 227} }
}
layer {
  name: "C1"
  type: "Convolution"
  bottom: "data"
  top: "C1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    kernel_size: 7
    stride: 4
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "C1"
  top: "C1"
}
layer {
  name: "S2"
  type: "Pooling"
  bottom: "C1"
  top: "S2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "norm2"
  type: "LRN"
  bottom: "S2"
  top: "norm2"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layer {
  name: "C3"
  type: "Convolution"
  bottom: "norm2"
  top: "C3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 2
    kernel_size: 5
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "C3"
  top: "C3"
}
layer {
  name: "S4"
  type: "Pooling"
  bottom: "C3"
  top: "S4"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "norm4"
  type: "LRN"
  bottom: "S4"
  top: "norm4"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layer {
  name: "C5"
  type: "Convolution"
  bottom: "norm4"
  top: "C5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer{
  name: "relu5" 
  type: "ReLU"
  bottom: "C5"
  top: "C5"
}
layer {
  name: "S6"
  type: "Pooling"
  bottom: "C5"
  top: "S6"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "F7"
  type: "InnerProduct"
  bottom: "S6"
  top: "F7"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 512
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu7"
  type: "ReLU"
  bottom: "F7"
  top: "F7"
}
layer {
  name: "drop7"
  type: "Dropout"
  bottom: "F7"
  top: "F7"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "F8"
  type: "InnerProduct"
  bottom: "F7"
  top: "F8"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 512
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu8"
  type: "ReLU"
  bottom: "F8"
  top: "F8"
}
layer {
  name: "drop8"
  type: "Dropout"
  bottom: "F8"
  top: "F8"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "F9bi"
  type: "InnerProduct"
  bottom: "F8"
  top: "F9bi"
  param {
    lr_mult: 10
    decay_mult: 1
  }
  param {
    lr_mult: 20
    decay_mult: 0
  }
  inner_product_param {
    num_output: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "prob"
  type: "Softmax"
  bottom: "F9bi"
  top: "prob"
}