BatchNorm Layer 是對輸入進行歸一化，消除過大噪點，有助於網路收斂

首先我們先看一下 BatchNormParameter

message BatchNormParameter {
	  // If false, accumulate global mean/variance values via a moving average.
	  // If true, use those accumulated values instead of computing mean/variance across the batch.
	  // 如果為真，則使用儲存的均值和方差，否則採用滑動平均計算新的均值和方差
      // 該引數預設的時候，如果是測試階段則等價為真，如果是訓練階段則等價為假
	  optional bool use_global_stats = 1;
	  
	  // How much does the moving average decay each iteration?
	  // 滑動平均的衰減係數，預設為0.999
	  optional float moving_average_fraction = 2 [default = .999];
	  
	  // Small value to add to the variance estimate so that we don't divide by zero.
	  // 分母附加值，防止除以方差時出現除0操作，預設為1e-5
	  optional float eps = 3 [default = 1e-5];
}
 

BatchNorm layer 在prototxt裡面的書寫：

layer {
 	name: "bn_conv1"
 	type: "BatchNorm"
    bottom: "conv1"
    top: "conv1"
  
    batch_norm_param {
        use_global_stats: true
    }
}

例如在MobileNet中：

layer {
	  name: "conv6_4/bn"
	  type: "BatchNorm"
	  bottom: "conv6_4"
	  top: "conv6_4/bn"
	  param {
	    lr_mult: 0
	    decay_mult: 0
	  }
	  param {
	    lr_mult: 0
	    decay_mult: 0
	  }
	  param {
	    lr_mult: 0
	    decay_mult: 0
	  }
	  batch_norm_param {
	    use_global_stats: true
	    eps: 1e-5
	  }
}