voc-fcn-alexnet網絡結構理解

一、寫在前面

fcn是首次使用cnn來實現語義分割的，論文地址：fully convolutional networks for semantic segmentation

實現代碼地址：https://github.com/shelhamer/fcn.berkeleyvision.org

全卷積神經網絡主要使用了三種技術：

1. 卷積化（Convolutional）

2. 上采樣（Upsample）

3. 跳躍結構（Skip Layer）

為了便於理解，我拿最簡單的結構voc-fcn-alexnet進行說明，該網絡結構主要用到了前面兩個技術，不包含跳躍結構。

 

二、voc-fcn-alexnet 的train.prototxt文件

layer {
  name: "data"
  type: "Python"
  top: "data"
  top: "label"
  python_param {
    module: "voc_layers"
    layer: "SBDDSegDataLayer"
    param_str: "{\'sbdd_dir\': \'../data/sbdd/dataset\', \'seed\': 1337, \'split\': \'train\', \'mean\': (104.00699, 116.66877, 122.67892)}"
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  convolution_param {
    num_output: 96
    pad: 100
    kernel_size: 11
    group: 1
    stride: 4
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  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"
  convolution_param {
    num_output: 256
    pad: 2
    kernel_size: 5
    group: 2
    stride: 1
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  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"
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    group: 1
    stride: 1
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "conv3"
  top: "conv4"
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    group: 2
    stride: 1
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv5"
  type: "Convolution"
  bottom: "conv4"
  top: "conv5"
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    group: 2
    stride: 1
  }
}
layer {
  name: "relu5"
  type: "ReLU"
  bottom: "conv5"
  top: "conv5"
}
layer {
  name: "pool5"
  type: "Pooling"
  bottom: "conv5"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "fc6"
  type: "Convolution"
  bottom: "pool5"
  top: "fc6"
  convolution_param {
    num_output: 4096
    pad: 0
    kernel_size: 6
    group: 1
    stride: 1
  }
}
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: "Convolution"
  bottom: "fc6"
  top: "fc7"
  convolution_param {
    num_output: 4096
    pad: 0
    kernel_size: 1
    group: 1
    stride: 1
  }
}
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: "score_fr"
  type: "Convolution"
  bottom: "fc7"
  top: "score_fr"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 21
    pad: 0
    kernel_size: 1
  }
}
layer {
  name: "upscore"
  type: "Deconvolution"
  bottom: "score_fr"
  top: "upscore"
  param {
    lr_mult: 0
  }
  convolution_param {
    num_output: 21
    bias_term: false
    kernel_size: 63
    stride: 32
  }
}
layer {
  name: "score"
  type: "Crop"
  bottom: "upscore"
  bottom: "data"
  top: "score"
  crop_param {
    axis: 2
    offset: 18
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "score"
  bottom: "label"
  top: "loss"
  loss_param {
    ignore_label: 255
    normalize: true
  }
}

 

三、網絡結構

假設輸入的圖片為500x500，

根據train.prototxt文件，可以得到上圖的網絡結構，該網絡結構除了前五層的卷積層，也把后面的三層改為了卷積層，score_fr是卷積層的最后一層，也叫heatmap熱圖，熱圖就是我們最重要的高維特診圖，得到高維特征的heatmap之后，就是最重要的一步也是最后的一步，對原圖像進行upsampling（即反卷積），把圖像進行放大，得到原圖像的大小。

四、損失函數

該網絡的損失函數為SoftmaxWithLoss。首先進行softmax求解，求出每個像素點屬於不同類別的概率，因為總共是分為21類，所以每個像素點對應21個概率值（輸出通道數為21）。然后求解每個像素點所屬實際類別概率的log值之和的平均，再取負數，可得到損失函數，參考如下：

end