name: “CaffeNet” //模型名
layer { //层
name: “data” //层名
type: “Input” //该层的类型
top: “data” //该层的输出
input_param { shape: { dim: 10 dim: 3 dim: 227 dim: 227 } }
}
layer {
name: “conv1” //卷积层1
type: “Convolution”
bottom: “data”//输入
top: “conv1”//输出
convolution_param { //参数
num_output: 96//输出个数
kernel_size: 11//卷积核大小11*11
stride: 4//步长
}
}
layer {
name: “relu1”
type: “ReLU”
bottom: “conv1”
top: “conv1”
}
layer {
name: “pool1”
type: “Pooling”
bottom: “conv1”
top: “pool1”
pooling_param {
pool: MAX//池化的方法,最大池化法
kernel_size: 3//核大小
stride: 2//步长
}
}
layer {
name: “norm1”
type: “LRN”
bottom: “pool1”
top: “norm1”
lrn_param {
local_size: 5 //对于cross channel LRN为需要 求和的邻近channel的数量;对于within channe