Caffe LeNet网络模型理解

Caffe的模型具有两个重要的参数文件：网络模型和参数配置，分别是*.prototxt和*.solver.prototxt

先上图：

//输入层
layer{
  name: "mnist"
  type: "Data"
  //input
  top: "data"
  top: "label"
  //数据输入定义:包含训练和测试数据
  include{
    phase:TRAIN
  }
  transform_param{
    scale: 0.00390625
  }
  data_param {
      source:"examples/minist/mnist_train_lmdb"//数据路径
      batch_size: 64 //批数据大小
      backend: LMDB
  }
}
//输出层
layer {
  name: "mnist"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param{
    scale: 0.00390625
  }
  data_param {
    source: "examples/mnist/mnist_test_lmdb"
    batch_size: 100
    backend: LMDB
  }
}
//卷积层
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1 //weight学习率
  }
  param {
    lr_mult: 2 //bias学习率，一般为weight的两倍
  }
  convolution_parm {
    num_output: 20//滤波器的个数
    kernel_size: 5//卷积核大小
    stride: 1//步长
    weight_filler{
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
//池化层
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
//全连接层
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool2"
  top: "ip1"
  param {
    lr_mult: 1//weight学习率
  }
  param {
    lr_mult: 2//bias学习率，一般为weight的两倍
  }
}
//ReLU激活函数，非线性变化层max(0,x)，一般与卷积层成对出现。
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "ip1"
  top: "ip1"
}
//LeNet SoftMax层如下
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "ip2"
  bottom: "label"
  top: "loss"
}

LeNet的参数配置文件：

# The train/test net protocol buffer definition
net: "examples/mnist/lenet_train_test.prototxt"
# test_iter specifies how many forward passes the test should carry out.
# In the case of MNIST, we have test batch size 100 and 100 test iterations,
# covering the full 10,000 testing images.
test_iter: 100
# Carry out testing every 500 training iterations.
test_interval: 500
# The base learning rate, momentum and the weight decay of the network.//学习速率，动量，权重衰减
base_lr: 0.01
momentum: 0.9
weight_decay: 0.0005
# The learning rate policy
lr_policy: "inv"
gamma: 0.0001
power: 0.75
# Display every 100 iterations//显示
display: 100
# The maximum number of iterations//最大迭代次数
max_iter: 10000
# snapshot intermediate results
snapshot: 5000
snapshot_prefix: "examples/mnist/lenet"
# solver mode: CPU or GPU//在何种模式下运行神经网络
solver_mode: CPU