caffe中mnist中 lenet

参照 http://blog.csdn.net/cham_3/article/details/52682479

http://blog.csdn.net/l18930738887/article/details/54898016

跑了下mnist训练，和使用训练好的模型进行预测

两个文件都在examples/mnist 中, lenet_train_test.prototxt 文件是设置train、test的网络，deploy文件是分类测试加载的文件。

大体区别思路是网络配置文件会规定的详细一些，deploy文件只是告诉分类程序（mnist_classification.bin）网络结构是怎么样的，不需要反向计算，不需要计算误差

两个文件内容先发出来：

cat lenet_train_test.prototxt 

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" }

cat lenet.prototxt   

name: "LeNet" layer { name: "data" type: "Input" top: "data" input_param { shape: { dim: 64 dim: 1 dim: 28 dim: 28 } } } 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: "prob" type: "Softmax" bottom: "ip2" top: "prob" }

区别：

1.首先删除TEST使用的部分，例如开始的输入数据test部分，

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 } }

最后的test精度部分

layer {   name: "accuracy"   type: "Accuracy"   bottom: "ip2"   bottom: "label"   top: "accuracy"   include {     phase: TEST   } }

2. trian部分的输入数据部分修改，只需要告诉输入维度

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   } }

改为

layer {   name: "data"   type: "Input"   top: "data"   input_param { shape: { dim: 64 dim: 1 dim: 28 dim: 28 } } }

shape: { dim: 64 dim: 1 dim: 28 dim: 28 }中第一个dim代表？，第二个dim代表channel个数1个（对于图片是RGB的，3通道就是3），第三第四个分别是width和height图片的。 

3. 原来的最后一层loss层改为pro层

layer { name: "loss" type: "SoftmaxWithLoss" bottom: "fc8" bottom: "label" top: "loss" } 1234567 1234567

A:将其中的SoftmaxWithLoss替换为Softmax  B:删除其中的bottom:”label”行，因为测试时需要预测label而不是给你一个已知label。  C:同时将最后一层loss层改为pro层  因此改完之后最后一层就是这样的：

layer { name: "prob" type: "Softmax" bottom: "fc8" top: "prob" } 123456 123456

这里的name: “prob”就是你在预测时读取的layer的name，一定要对应上