GoogLeNet inception module as a caffe net

name: "Inception_3a"

input: "maxpool_2"
input_dim: 1
input_dim: 192
input_dim: 28
input_dim: 28

layers {
  name: "1x1_conv"
  type: CONVOLUTION
  bottom: "maxpool_2"
  top: "1x1_conv"
  blobs_lr: 1
  blobs_lr: 2
  convolution_param {
    num_output: 64
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}

layers {
  name: "1x1_relu"
  type: RELU
  bottom: "1x1_conv"
  top: "1x1_relu"
}

layers {
  name: "3x3reduce_conv"
  type: CONVOLUTION
  bottom: "maxpool_2"
  top: "3x3reduce_conv"
  blobs_lr: 1
  blobs_lr: 2
  convolution_param {
    num_output: 96
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}

layers {
  name: "3x3reduce_relu"
  type: RELU
  bottom: "3x3reduce_conv"
  top: "3x3reduce_relu"
}

layers {
  name: "3x3_conv"
  type: CONVOLUTION
  bottom: "3x3reduce_relu"
  top: "3x3_conv"
  blobs_lr: 1
  blobs_lr: 2
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}

layers {
  name: "3x3_relu"
  type: RELU
  bottom: "3x3_conv"
  top: "3x3_relu"
}

layers {
  name: "5x5reduce_conv"
  type: CONVOLUTION
  bottom: "maxpool_2"
  top: "5x5reduce_conv"
  blobs_lr: 1
  blobs_lr: 2
  convolution_param {
    num_output: 16
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}

layers {
  name: "5x5reduce_relu"
  type: RELU
  bottom: "5x5reduce_conv"
  top: "5x5reduce_relu"
}

layers {
  name: "5x5_conv"
  type: CONVOLUTION
  bottom: "5x5reduce_relu"
  top: "5x5_conv"
  blobs_lr: 1
  blobs_lr: 2
  convolution_param {
    num_output: 32
    pad: 2
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}

layers {
  name: "5x5_relu"
  type: RELU
  bottom: "5x5_conv"
  top: "5x5_relu"
}

layers {
  name: "maxpool_3x3"
  type: POOLING
  bottom: "maxpool_2"
  top: "maxpool_3x3"
  pooling_param {
    pool: MAX
    pad: 1
    kernel_size: 3
    stride: 1
  }
}

layers {
  name: "poolproj_1x1conv"
  type: CONVOLUTION
  bottom: "maxpool_3x3"
  top: "poolproj_1x1conv"
  blobs_lr: 1
  blobs_lr: 2
  convolution_param {
    num_output: 32
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}

layers {
  name: "poolproj_relu"
  type: RELU
  bottom: "poolproj_1x1conv"
  top: "poolproj_relu"
}

layers {
  name: "DepthConcatenation"
  type: CONCAT
  concat_param {
    concat_dim: 1
  }
  bottom: "1x1_relu"
  bottom: "3x3_relu"
  bottom: "5x5_relu"
  bottom: "poolproj_relu"
  top: "inception3a_Output"
}

@jyegerlehner thanks for this implementation. I am implementing the inception module in C and I have some issues understanding this fully. If you can shed some light on any of the following it would be great:

1. Where do we get the filters and number of filters to apply from? In Table 1 of the paper, the inception (3a) module seems to get as input a 28x28x192 matrix. To it, 64 1x1 filters (I am assuming each of them have 192 channels each?) are applied; 128 3x3 filters (each filter with 96(as there are 96 1x1 before that) channels); and 32 5x5 filters (each filter with 16 channels). Are these numbers (the number of filters for each type) just made up the authors through trial and error or is there more general way of generating these numbers?
2. What is "AveragePool", "SoftmaxActivation" and "FC"and how does one go about implementing it?

I would be very obliged if you could guide me in the right direction!