如何使用如意工作室将MobileNet-SSD .caffemodel转换为.wk文件？

Hello, I have a question that how to covert MobileNet-SSD .caffemodel to .wk file using Ruyi studio? My model does not contain Batch Normallization Layers, so what changes in need to make in the original  .prototxt file? My current .prototxt file is attached.  

 

This is my current .prototxt file. 

name: "MobileNet-SSD"
input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 300
  dim: 300
}
layer {
  name: "conv0"
  type: "Convolution"
  bottom: "data"
  top: "conv0"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  convolution_param {
    num_output: 32
    bias_term: true
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv0/relu"
  type: "ReLU"
  bottom: "conv0"
  top: "conv0"
}
layer {
  name: "conv1/dw"
  type: "Convolution"
  bottom: "conv0"
  top: "conv1/dw"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  convolution_param {
    num_output: 32
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 32
    weight_filler {
      type: "msra"
    }
    engine: CAFFE
  }
}
layer {
  name: "conv1/dw/relu"
  type: "ReLU"
  bottom: "conv1/dw"
  top: "conv1/dw"
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "conv1/dw"
  top: "conv1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  convolution_param {
    num_output: 64
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv1/relu"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "conv2/dw"
  type: "Convolution"
  bottom: "conv1"
  top: "conv2/dw"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  convolution_param {
    num_output: 64
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 64
    stride: 2
    weight_filler {
      type: "msra"
    }
    engine: CAFFE
  }
}
layer {
  name: "conv2/dw/relu"
  type: "ReLU"
  bottom: "conv2/dw"
  top: "conv2/dw"
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "conv2/dw"
  top: "conv2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  convolution_param {
    num_output: 128
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv2/relu"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "conv3/dw"
  type: "Convolution"
  bottom: "conv2"
  top: "conv3/dw"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  convolution_param {
    num_output: 128
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 128
    weight_filler {
      type: "msra"
    }
    engine: CAFFE
  }
}
layer {
  name: "conv3/dw/relu"
  type: "ReLU"
  bottom: "conv3/dw"
  top: "conv3/dw"
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "conv3/dw"
  top: "conv3"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  convolution_param {
    num_output: 128
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv3/relu"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv4/dw"
  type: "Convolution"
  bottom: "conv3"
  top: "conv4/dw"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  convolution_param {
    num_output: 128
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 128
    stride: 2
    weight_filler {
      type: "msra"
    }
    engine: CAFFE
  }
}
layer {
  name: "conv4/dw/relu"
  type: "ReLU"
  bottom: "conv4/dw"
  top: "conv4/dw"
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "conv4/dw"
  top: "conv4"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  convolution_param {
    num_output: 256
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv4/relu"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv5/dw"
  type: "Convolution"
  bottom: "conv4"
  top: "conv5/dw"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  convolution_param {
    num_output: 256
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 256
    weight_filler {
      type: "msra"
    }
    engine: CAFFE
  }
}
layer {
  name: "conv5/dw/relu"
  type: "ReLU"
  bottom: "conv5/dw"
  top: "conv5/dw"
}
layer {
  name: "conv5"
  type: "Convolution"
  bottom: "conv5/dw"
  top: "conv5"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  convolution_param {
    num_output: 256
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv5/relu"
  type: "ReLU"
  bottom: "conv5"
  top: "conv5"
}
layer {
  name: "conv6/dw"
  type: "Convolution"
  bottom: "conv5"
  top: "conv6/dw"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  convolution_param {
    num_output: 256
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 256
    stride: 2
    weight_filler {
      type: "msra"
    }
    engine: CAFFE
  }
}
layer {
  name: "conv6/dw/relu"
  type: "ReLU"
  bottom: "conv6/dw"
  top: "conv6/dw"
}
layer {
  name: "conv6"
  type: "Convolution"
  bottom: "conv6/dw"
  top: "conv6"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  convolution_param {
    num_output: 512
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }