caffe实例-LeNet简介与mnist

https://www.cnblogs.com/cookcoder-mr/p/4452119.html

装好caffe之后，下面我们来跑它自带的第一个例子，在mnist进行实验，参见http://caffe.berkeleyvision.org/gathered/examples/mnist.html

（1）caffe在mnist自带的是使用leNet的网络结构。

   1.简介：

  LeNet论文是Yan LeCun在1989年的论文Gradient-Based Learning Applied to Document Recognition

   http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf,这是CNN第一篇经典之作.

   minst是手写字体库，CNN的LeNet的广泛应用于美国的支票手写字体识别。

   2.LeNet网络结构

   

 

（2）在mnist 进行实验

  均在caffe根目录下执行

•   1.下载数据：  ./data/mnist/get_mnist.sh,
•   2.生成lmdb文件：./example/mnist/create_minist.sh
•    此时在当前目录下生成 mnist_train_lmdb,mnist_test_lmdb文件
•   3.配置网络 ：letNet网络的定义在。./examples/mnist/lenet_train_test.prototxt文件中

 lenet_train_test.prototxt内容如下

View Code

name: "LeNet"  2 layers {  3   name: "mnist"  4   type: DATA  5   top: "data"  6   top: "label"  7   data_param {  8     source: "examples/mnist/mnist_train_lmdb"  9     backend: LMDB 10     batch_size: 64 11   } 12   transform_param { 13     scale: 0.00390625 14   } 15   include: { phase: TRAIN } 16 } 17 layers { 18   name: "mnist" 19   type: DATA 20   top: "data" 21   top: "label" 22   data_param { 23     source: "examples/mnist/mnist_test_lmdb" 24     backend: LMDB 25     batch_size: 100 26   } 27    transform_param { 28     scale: 0.00390625 29   } 30   include: { phase: TEST } 31 } 32  33 layers { 34   name: "conv1" 35   type: CONVOLUTION 36   bottom: "data" 37   top: "conv1" 38   blobs_lr: 1 39   blobs_lr: 2 40   convolution_param { 41     num_output: 20 42     kernel_size: 5 43     stride: 1 44     weight_filler { 45       type: "xavier" 46     } 47     bias_filler { 48       type: "constant" 49     } 50   }51  } 52 layers { 53   name: "pool1" 54   type: POOLING 55   bottom: "conv1" 56   top: "pool1" 57   pooling_param { 58     pool: MAX 59     kernel_size: 2 60     stride: 2 61   } 62 } 63 layers { 64   name: "conv2" 65   type: CONVOLUTION 66   bottom: "pool1" 67   top: "conv2" 68   blobs_lr: 1 69   blobs_lr: 2 70   convolution_param { 71     num_output: 50 72     kernel_size: 5 73     stride: 1 74     weight_filler {75     type: "xavier" 76     } 77     bias_filler { 78       type: "constant" 79     } 80   } 81 } 82 layers { 83   name: "pool2" 84   type: POOLING 85   bottom: "conv2" 86   top: "pool2" 87   pooling_param { 88     pool: MAX 89     kernel_size: 2 90     stride: 2 91   } 92 } 93 layers { 94   name: "ip1" 95   type: INNER_PRODUCT 96   bottom: "pool2" 97   top: "ip1" 98   blobs_lr: 1 99   blobs_lr: 2100   inner_product_param {101  num_output: 500102     weight_filler {103       type: "xavier"104     }105     bias_filler {106       type: "constant"107     }108   }109 }110 layers {111   name: "relu1"112   type: RELU113   bottom: "ip1"114   top: "ip1"115 }116 layers {117   name: "ip2"118   type: INNER_PRODUCT119   bottom: "ip1"120   top: "ip2"121   blobs_lr: 1122   blobs_lr: 2123   inner_product_param {124     num_output: 10125     weight_filler {126       type: "xavier"127     }128     bias_filler {129       type: "constant"130     }131   }132 }133 layers {134   name: "accuracy"135   type: ACCURACY136   bottom: "ip2"137   bottom: "label"138   top: "accuracy"139   include: { phase: TEST }140 }141 layers {142   name: "loss"143   type: SOFTMAX_LOSS144   bottom: "ip2"145   bottom: "label"146   top: "loss"147 }

•    4、运行 ./example/mnist/train_lenet.sh  

   train_lenet.sh内容为

  1 #!/usr/bin/env sh
  2 
  3 ./build/tools/caffe train --solver=examples/mnist/lenet_solver.prototxt

 它其实使用的是在lenet_solver.prototxt中定义的解决方案

 lenet_solver.prototxt内容是

1 # The train/test net protocol buffer definition  2 net: "examples/mnist/lenet_train_test.prototxt"  3 # test_iter specifies how many forward passes the test should carry out.  4 # In the case of MNIST, we have test batch size 100 and 100 test iterations,  5 # covering the full 10,000 testing images.  6 test_iter: 100  7 # Carry out testing every 500 training iterations.  8 test_interval: 500  9 # The base learning rate, momentum and the weight decay of the network. 10 base_lr: 0.01 11 momentum: 0.9 12 weight_decay: 0.0005 13 # The learning rate policy 14 lr_policy: "inv" 15 gamma: 0.0001 16 power: 0.75 17 # Display every 100 iterations 18 display: 100 19 # The maximum number of iterations 20 max_iter: 10000 21 # snapshot intermediate results 22 snapshot: 5000 23 snapshot_prefix: "examples/mnist/lenet" 24 # solver mode: CPU or GPU 25 solver_mode: GPU

• 5.查看实验结果：

   经过一系列迭代iteration之后，在mnist上识别正确率能达到99.11%