caffe CNN train_val.prototxt 神经网络参数配置说明

name: "CaffeNet"
layer {
#输入层，即数据层
#数据层的类型除了Database外，还可以是In-Memory、HDF5 Input、HDF5 Output、Images、Windows、Dummy
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
	#表示仅在训练阶段包括进去
  }
  transform_param {
  #对数据进行预处理，依次是做镜像，设定crop大小，减去均值文件
    mirror: true
    crop_size: 60
    mean_file: "/home/stack/caffe-master/data/HQPData/0902/img0902_mean.binaryproto"
  }
  data_param {
  #设定数据来源
    source: "/home/stack/caffe-master/examples/HuQPTask/0902/train_lmdb"
	#包含数据的目录名称
    batch_size: 50
	#一次处理的输入的数量
    backend: LMDB
	#选择使用 LEVELDB 或者 LMDB
  }
}
layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param {
    mirror: true
    crop_size: 60
    mean_file: "/home/stack/caffe-master/data/HQPData/0902/img0902_mean.binaryproto"
  }
  data_param {
    source: "/home/stack/caffe-master/examples/HuQPTask/0902/val_lmdb"
    batch_size: 50
    backend: LMDB
  }
}
layer {
#Convolution
#卷积层
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
  #过滤器/权重 参数
    lr_mult: 1
	# learning rate multiplier for the filters
	#学习率倍数
    decay_mult: 1
	# weight decay multiplier for the filters
	#权重衰减率
  }
  param {
  #偏置 参数
    lr_mult: 2
	# learning rate multiplier for the biases
	#学习率倍数
    decay_mult: 0
	# weight decay multiplier for the biases
	#权重衰减率
  }
  convolution_param {
    num_output: 96
	# learn 96 filters
    kernel_size: 3
	# each filter is 3x3
    stride: 1
	# step 1 pixels between each filter application
    weight_filler {
	#初始化权重/过滤器：均值默认为0，标准差0.01的高斯函数
      type: "gaussian"
	  # initialize the filters from a Gaussian
      std: 0.01
	  # distribution with stdev 0.01 (default mean: 0)  
    }
    bias_filler {
	#初始化偏置：常数0
	# initialize the biases to zero (0)
      type: "constant"	  
      value: 0
    }
  }
}
layer {
#Rectified-Linear and Leaky-ReLU 校正线性
#Activation / Neuron Layers 激励层，除了ReLu外，还可以用Sigmoid、TanH 、Absolute Value、Power、BNLL
#ReLU是目前使用做多的激励函数，主要因为其收敛更快，并且能保持同样效果。
#标准的ReLU函数为max(x, 0)，而一般为当x > 0时输出x，但x <= 0时输出negative_slope。RELU层支持in-place计算，这意味着bottom的输出和输入相同以避免内存的消耗。
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
#Pooling 下采样层
#池化层
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
	#pooling的方法，目前有MAX, AVE, 和STOCHASTIC三种方法
    kernel_size: 3
	# pool over a 3x3 region
    stride: 2
	# step two pixels (in the bottom blob) between pooling regions
  }
}
layer {
#Local Response Normalization 
#局部输入区域归一化
#这里需要看公式，以下参数是指公式中的参数
  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"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 2
    kernel_size: 5
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 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: 1
  }
}
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"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "conv3"
  top: "conv4"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv5"
  type: "Convolution"
  bottom: "conv4"
  top: "conv5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 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 {
#Common Layers
#全连接层 Inner Product
  name: "fc6"
  type: "InnerProduct"
  bottom: "pool5"
  top: "fc6"
  param {
    lr_mult: 1
	# learning rate multiplier for the filters
    decay_mult: 1
	# weight decay multiplier for the filters
  }
  param {
    lr_mult: 2
	# learning rate multiplier for the biases
    decay_mult: 0
	# weight decay multiplier for the biases
  }
  inner_product_param {
    num_output: 4096
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 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
	#丢弃数据的概率
  }
}
layer {
  name: "fc7"
  type: "InnerProduct"
  bottom: "fc6"
  top: "fc7"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 4096
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 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: "fc8"
  type: "InnerProduct"
  bottom: "fc7"
  top: "fc8"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
#Loss Layers损耗层
#Accuracy准确率层（计算准确率）用来计算输出和目标的正确率
#事实上这不是一个loss，而且没有backward这一步。
  name: "accuracy"
  type: "Accuracy"
  bottom: "fc8"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
#损失估计层
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "fc8"
  bottom: "label"
  top: "loss"
}