深度学习_caffe (4) 基于mnist实例搭建新的神经网络&在caffe中添加层（续1）

如何在caffe中添加层：
http://www.voidcn.com/blog/wangzhebupt/article/p-4946427.html
http://blog.sciencenet.cn/home.php?mod=space&uid=1583812&do=blog&id=850247
http://blog.csdn.net/kuaitoukid/article/details/41865803
怎么在caffe中配置每一个层的结构：
http://www.myexception.cn/other/1828071.html

---

上一篇 看到了lenet_solver.prototxt
其中net: “examples/mnist/lenet_train_test.prototxt”指定了网络模型，打开lenet_train_test.prototxt看一下

name: "LeNet"
layer {
  name: "mnist"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "examples/mnist/mnist_train_lmdb"
    batch_size: 64
    backend: LMDB
  }
}
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
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 20
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 50
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool2"
  top: "ip1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "ip1"
  top: "ip1"
}
layer {
  name: "ip2"
  type: "InnerProduct"
  bottom: "ip1"
  top: "ip2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 10
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "ip2"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "ip2"
  bottom: "label"
  top: "loss"
}

全是一层一层的定义，也就是神经网络模型各个层的组合方式声明。
关于这些层结构的参数和详细解释 可以参考caffe官网给出的资料。http://blog.csdn.net/u013369277/article/details/51351230
看到这里可以回顾一下
运行mnist
首先是运行一个.sh文件
time sh examples/mnist/train_lenet.sh
然后.sh文件里是 solver.prototxt文件
solver.prototxt 里面定义了 net 和一些迭代什么的 参数
net是由 另一个prototxt文件详细定义的。
所以到目前为止 如果要仿写模型的话 可以先写好这三个文件夹。搭好框架 然后再最后一个prototxt中 调用各个层 组合自己的模型就好了。