net.prototxt

name: "CNN"
input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 224
  dim: 224
}

layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  convolution_param {
    num_output: 16
    kernel_size: 3
    pad: 1
    stride: 1
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
  relu_param{
    negative_slope: 0.1
  }		
}
layer {
  name: "max_pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "max_pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}

layer{
  name: "conv2"
  type: "Convolution"
  bottom: "max_pool1"
  top: "conv2"
  convolution_param {
    num_output: 32
    kernel_size: 3
    pad: 1
    stride: 1
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
  relu_param{
    negative_slope: 0.1
  }		
}
layer {
  name: "max_pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "max_pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}

layer{
  name: "conv3"
  type: "Convolution"
  bottom: "max_pool2"
  top: "conv3"
  convolution_param {
    num_output: 64
    kernel_size: 3
    pad: 1
    stride: 1
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
  relu_param{
    negative_slope: 0.1
  }		
}

layer {
  name: "max_pool3"
  type: "Pooling"
  bottom: "conv3"
  top: "max_pool3"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}


layer{
  name: "conv4"
  type: "Convolution"
  bottom: "max_pool3"
  top: "conv4"
  convolution_param {
    num_output: 128
    kernel_size: 3
    pad: 1
    stride: 1
  }
}

layer {
  name: "relu4"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
  relu_param{
    negative_slope: 0.1
  }		
}

layer {
  name: "max_pool4"
  type: "Pooling"
  bottom: "conv4"
  top: "max_pool4"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}


layer{
  name: "conv5"
  type: "Convolution"
  bottom: "max_pool4"
  top: "conv5"
  convolution_param {
    num_output: 256
    kernel_size: 3
    pad: 1
    stride: 1
  }
}
layer {
  name: "relu5"
  type: "ReLU"
  bottom: "conv5"
  top: "conv5"
  relu_param{
    negative_slope: 0.1
  }		
}
layer {
  name: "max_pool5"
  type: "Pooling"
  bottom: "conv5"
  top: "max_pool5"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}

layer{
  name: "conv6"
  type: "Convolution"
  bottom: "max_pool5"
  top: "conv6"
  convolution_param {
    num_output: 512
    kernel_size: 3
    pad: 1
    stride: 1
  }
}
layer {
  name: "relu6"
  type: "ReLU"
  bottom: "conv6"
  top: "conv6"
  relu_param{
    negative_slope: 0.1
  }		
}
layer {
  name: "max_pool6"
  type: "Pooling"
  bottom: "conv6"
  top: "max_pool6"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}

layer{
  name: "conv7"
  type: "Convolution"
  bottom: "max_pool6"
  top: "conv7"
  convolution_param {
    num_output: 1024
    kernel_size: 3
    pad: 1
    stride: 1
  }
}
layer {
  name: "relu7"
  type: "ReLU"
  bottom: "conv7"
  top: "conv7"
  relu_param{
    negative_slope: 0.1
  }		
}

layer {
  name: "ave_pool7"
  type: "Pooling"
  bottom: "conv7"
  top: "ave_pool7"
  pooling_param {
    pool: AVE
    kernel_size: 2
    stride: 2
  }
}

layer{
  name: "Fully Connected"
  type: "InnerProduct"
  bottom: "ave_pool7"
  top: "result"
  inner_product_param {
    num_output: 7
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}