数据层: layer { name: "mnist"//名字mnist type: "Data"//类型data top: "data"//输出数据 top: "label"//输出标签 include { phase: TRAIN } transform_param { scale: 0.00390625//归一化 {0-255}->{0-1} } data_param { source: "examples/mnist/mnist_train_lmdb" batch_size: 64 backend: LMDB } } 卷积层 layer { name: "conv1" type: "Convolution" bottom: "data"//输入data blob top: "conv1"//输出conv1 param { lr_mult: 1//权重学习率倍乘因子。乘以全局学习率 } param { lr_mult: 2//偏置学习率倍乘因子。乘以全局学习率 } convolution_param { num_output: 20//cov1层将产生输出20个通道 kernel_size: 5//卷积核大小是5*5 stride: 1//步长是1 weight_filler {//权重初始化方法,使用xavier算法填充weight。 type: "xavier" } bias_filler {//偏置初始化方法,使用constant算法填充bias。默认是常数0 type: "constant" } } } 池化层 layer { name: "pool1" type: "Pooling" bottom: "conv1" top: "pool1" pooling_param { pool: MAX//使用MAX进行池化 kernel_size: 2//卷积核大小是2*2 stride: 2//步长是2 } } 全连接层 layer { name: "ip1" type: "InnerProduct" bottom: "pool2" top: "ip1" param { lr_mult: 1 } param { lr_mult: 2 } inner_product_param { num_output: 500//产生500维的输出数据 weight_filler { type: "xavier" } bias_filler { type: "constant" } } } ReLU层 layer { name: "relu1" type: "ReLU" bottom: "ip1" top: "ip1" } Loss层 layer { name: "loss" type: "SoftmaxWithLoss" bottom: "ip2" bottom: "label"//来自数据层的标签 top: "loss" }
转载请注明原文地址: https://www.6miu.com/read-70606.html