caffe 实践程序4——cifar10网络

cifar10是个中小型的图片数据库，总共60000张32*32大小的图片，5w张用于训练，1w张用于测试。

caffe上cifar10的训练流程。

cifar10_quick_train_test.prototxt

name: "CIFAR10_quick"layer {  name: "cifar"  type: "Data"  top: "data"  top: "label"  include {    phase: TRAIN  }  transform_param {    mean_file: "examples/cifar10/mean.binaryproto"  }  data_param {    source: "examples/cifar10/cifar10_train_lmdb"    batch_size: 100    backend: LMDB  }}layer {  name: "cifar"  type: "Data"  top: "data"  top: "label"  include {    phase: TEST  }  transform_param {    mean_file: "examples/cifar10/mean.binaryproto"  }  data_param {    source: "examples/cifar10/cifar10_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: 32    pad: 2    kernel_size: 5    stride: 1    weight_filler {      type: "gaussian"      std: 0.0001    }    bias_filler {      type: "constant"    }  }}layer {  name: "pool1"  type: "Pooling"  bottom: "conv1"  top: "pool1"  pooling_param {    pool: MAX    kernel_size: 3    stride: 2  }}layer {  name: "relu1"  type: "ReLU"  bottom: "pool1"  top: "pool1"}layer {  name: "conv2"  type: "Convolution"  bottom: "pool1"  top: "conv2"  param {    lr_mult: 1  }  param {    lr_mult: 2  }  convolution_param {    num_output: 32    pad: 2    kernel_size: 5    stride: 1    weight_filler {      type: "gaussian"      std: 0.01    }    bias_filler {      type: "constant"    }  }}layer {  name: "relu2"  type: "ReLU"  bottom: "conv2"  top: "conv2"}layer {  name: "pool2"  type: "Pooling"  bottom: "conv2"  top: "pool2"  pooling_param {    pool: AVE    kernel_size: 3    stride: 2  }}layer {  name: "conv3"  type: "Convolution"  bottom: "pool2"  top: "conv3"  param {    lr_mult: 1  }  param {    lr_mult: 2  }  convolution_param {    num_output: 64    pad: 2    kernel_size: 5    stride: 1    weight_filler {      type: "gaussian"      std: 0.01    }    bias_filler {      type: "constant"    }  }}layer {  name: "relu3"  type: "ReLU"  bottom: "conv3"  top: "conv3"}layer {  name: "pool3"  type: "Pooling"  bottom: "conv3"  top: "pool3"  pooling_param {    pool: AVE    kernel_size: 3    stride: 2  }}layer {  name: "ip1"  type: "InnerProduct"  bottom: "pool3"  top: "ip1"  param {    lr_mult: 1  }  param {    lr_mult: 2  }  inner_product_param {    num_output: 64    weight_filler {      type: "gaussian"      std: 0.1    }    bias_filler {      type: "constant"    }  }}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: "gaussian"      std: 0.1    }    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"}

之前做可视化，导师想通过改变网络层数训练模型，进而观察可视化结果，来评估网络好坏程度及为修改网络参数提供方案。

一张32*32大小的图片输入网络，变动如下：

conv1     100     32     32*32pool1     100     32     16*16conv2     100     32     16*16pool2     100     32     8*8conv3     100     64     8*8pool3     100     64     4*4ip1       100     64     1*1ip1       100     10     1*1

因为conv1中的pad参数，所以从conv1出来的大小为（32+2×pad-kernel_size+stride）/stride=32，即输入是32*32，输出也是32*32。

现在在原网络增加两大层（一个大层是指：conv，pool，relu），中间有5大层时，网络已达极限，因为原始图片为32*32大小，

网络5：data ->cpr1->crp2->crp3->crp4->crp5->ip1->ip2    识别率：53%  52.29%

若再增加层数识别率均为10%，现原因不明