Caffe基础（二）-使用命令行方式训练预测mnist、cifar10及自己的数据集

在win10 vs2015 显卡compute capability7.5 Python3.5.2环境下配置caffe及基本使用（一）介绍了如何编译生成caffe工程及python、matlab接口。下面介绍通过命令行方式使用caffe训练预测mnist数据集、训练预测cifar10数据集，训练预测自己的数据集。

(1) 训练mnist数据集

在主目录下的examples/minst文件夹下放入minist数据集

                               

数据集见链接

可以用如下两个bat文件来做mnist数据集的转换

如下是转换为leveldb数据格式

 

如下是转换为lmdb格式

                                            

在主目录下新建一个bat文件my_add_mnist_run_train.bat(名字可以随意定义），输入如下内容：

打开lenet_solver.prototxt,可以看到

# The train/test net protocol buffer definition
net: "examples/mnist/lenet_train_test.prototxt"
# test_iter specifies how many forward passes the test should carry out.
# In the case of MNIST, we have test batch size 100 and 100 test iterations,
# covering the full 10,000 testing images.
test_iter: 100
# Carry out testing every 500 training iterations.
test_interval: 500
# The base learning rate, momentum and the weight decay of the network.
base_lr: 0.01
momentum: 0.9
weight_decay: 0.0005
# The learning rate policy
lr_policy: "inv"
gamma: 0.0001
power: 0.75
# Display every 100 iterations
display: 100
# The maximum number of iterations
max_iter: 10000
# snapshot intermediate results
snapshot: 5000
snapshot_prefix: "examples/mnist/lenet"
# solver mode: CPU or GPU
solver_mode: GPU

里面有学习率，迭代步数，gpu还是使用cpu跑等配置

再打开lenet_train_test.prototxt文件，可以看到

可以将prototxt文件放在以下的网址，查看网络的结构：http://ethereon.github.io/netscope/#/editor

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"
}

里面有网络结构、各层过滤器的大小，步长设置及数据集设置，有对应自己框架的数据结构

运行该训练的bat文件，训练完毕后结果如下：

（2）用训练出来的模型测试mnist

首先计算mean.binaryproto

bat文件内容如下：

将lenet_train_test.prototxt复制一份出来，改名为my_lenet_test.prototxt，取名随意

对比lenet_train_test.prototxt，增加下面红色标记处语句：

                                        

在主目录下新建一个bat文件，文件里内容为：

运行该bat文件，结果如下：

                      

创建一个bat文件，对单张mnist图片进行预测，文件里语句如下：

test image文件夹中里的内容如下：

                                              

result.txt中的内容如下（这里是caffe预测的结果为一个10维向量，这里预测的图片是2，会得到该向量中最大值所处的索引值，凭该索引去result中找对应的类别标签）：

     

                                                                

该bat文件的执行结果如下：

（3）训练cifar10

首先转化cifar10为caffe能够支持的数据集格式，这里转为lmdb,原来的数据集格式如下：

                                                     

转化的bat文件中的语句如下：

创建bat文件计算cifar10的mean.binaryproto文件

创建bat文件训练网络

cifar10_quick_solver.prototxt文件如下：

                               

cifar10_quick_train_test.prototxt文件如下：

name: "CIFAR10_quick"
layer {
  name: "cifar"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mean_file: "./examples/cifar10/cifar_outputdata/mean.binaryproto"
  }
  data_param {
    source: "./examples/cifar10/cifar_outputdata/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/cifar_outputdata/mean.binaryproto"
  }
  data_param {
    source: "./examples/cifar10/cifar_outputdata/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"
}

（4）命令行方式使用caffe预测一张cifar10图片

如上mnist预测一样，预测图片如下：

                                                                              

同样需要类别标签名文件synset_words.txt，供caffe的结果去索引，该文件内容如下：

                                                                      

预测bat文件如下：

运行结果如下：

 

（5）训练自己的数据集

在根目录下data文件夹下新建mydata文件夹，需要训练的数据集会存放在该文件夹内。

新建一个train和val文件夹,每个文件夹内如下：

                                                       

cat文件夹内图片如下：

dog文件夹内图片如下：

同时在mydata文件夹内新建train.txt和val.txt，以记录这些图片的路径

                                                                   

                                                                     

 

在主目录下创建bat文件，该文件将jpg图片转化为LMDB数据格式

新建bat文件，计算mean.binaryproto

这里选择利用cifar10中的cifar10_full_solver.prototxt、cifar10_full_train_test.prototxt，在其基础上进行修改，主要是修改了batch size，因为我这边的数据集很小，此外输出类别种类数由10改为了2

新建bat文件，训练网络

solve.prototxt中的内容如下：

# reduce learning rate after 120 epochs (60000 iters) by factor 0f 10
# then another factor of 10 after 10 more epochs (5000 iters)

# The train/test net protocol buffer definition
net: "./data/mydata/train_val.prototxt"
# test_iter specifies how many forward passes the test should carry out.
# In the case of CIFAR10, we have test batch size 100 and 100 test iterations,
# covering the full 10,000 testing images.
test_iter: 4
# Carry out testing every 1000 training iterations.
test_interval: 4
# The base learning rate, momentum and the weight decay of the network.
base_lr: 0.001
momentum: 0.9
weight_decay: 0.004
# The learning rate policy
lr_policy: "fixed"
# Display every 200 iterations
display: 4
# The maximum number of iterations
max_iter: 6000
# snapshot intermediate results
snapshot: 2000
snapshot_format: HDF5
snapshot_prefix: "./data/mydata/full"
# solver mode: CPU or GPU
solver_mode: GPU

train_val.prototxt中的内容如下：

name: "CIFAR10_full"
layer {
  name: "cifar"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mean_file: "./data/mydata/mean.binaryproto"
  }
  data_param {
    source: "./data/mydata/mtrain"
    batch_size: 4
    backend: LMDB
  }
}
layer {
  name: "cifar"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param {
    mean_file: "./data/mydata/mean.binaryproto"
  }
  data_param {
    source: "./data/mydata/mval"
    batch_size: 2
    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: "norm1"
  type: "LRN"
  bottom: "pool1"
  top: "norm1"
  lrn_param {
    local_size: 3
    alpha: 5e-05
    beta: 0.75
    norm_region: WITHIN_CHANNEL
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "norm1"
  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: "norm2"
  type: "LRN"
  bottom: "pool2"
  top: "norm2"
  lrn_param {
    local_size: 3
    alpha: 5e-05
    beta: 0.75
    norm_region: WITHIN_CHANNEL
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "norm2"
  top: "conv3"
  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
    decay_mult: 250
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "ip1"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "ip1"
  bottom: "label"
  top: "loss"
}

运行bat文件，生成caffe.model文件

新建deploy.prototxt文件，该文件是由上面的train_val.prototxt修改而成

deploy.prototxt文件和train_val.prototxt文件不同的地方在于：

（1）输入的数据不再是LMDB，也不分为测试集和训练集，输入的类型为Input，定义的维度，和训练集的数据维度保持一致，121*121，否则会报错；

（2）去掉weight_filler和bias_filler，这些参数已经存在于caffemodel中了，由caffemodel进行初始化。

（3）去掉最后的Accuracy层和loss层，换位Softmax层，表示分为某一类的概率。

deploy.prototxt文件如下：

name: "CIFAR10_full"
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param{shape: {dim:1 dim:3 dim:121 dim:121}}
}

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    
  }
}
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: "norm1"
  type: "LRN"
  bottom: "pool1"
  top: "norm1"
  lrn_param {
    local_size: 3
    alpha: 5e-05
    beta: 0.75
    norm_region: WITHIN_CHANNEL
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "norm1"
  top: "conv2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 32
    pad: 2
    kernel_size: 5
    stride: 1
  }
}
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: "norm2"
  type: "LRN"
  bottom: "pool2"
  top: "norm2"
  lrn_param {
    local_size: 3
    alpha: 5e-05
    beta: 0.75
    norm_region: WITHIN_CHANNEL
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "norm2"
  top: "conv3"
  convolution_param {
    num_output: 64
    pad: 2
    kernel_size: 5
    stride: 1 
  }
}
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
    decay_mult: 250
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
    }
  }
}

layer {
  name: "prob"
  type: "Softmax"
  bottom: "ip1"
  top: "prob"
}

运行结果如下：

测试图片为

可知预测结果正确

这里附上以上相关文件链接

主目录下的examples\mnist文件夹内文件链接：https://pan.baidu.com/s/1H2tlBFEun-EPXSDn5uH8xg 
提取码：15xl 
主目录下的examples\cifar10文件夹内文件python、matlab调用）链接：https://pan.baidu.com/s/17Sy5mKtaFMEyB4_CEyAyrA 
提取码：5c1j 
主目录下的\data\mydata文件夹内的文件 链接：https://pan.baidu.com/s/1deI-ka1CoIvJdgx9cyEhSQ 
提取码：xgct

command line 文件 链接：https://pan.baidu.com/s/1kJONutsQlkN5KJ-n-lPmyg 
提取码：5snd

后续会有博客介绍如何使用matlab、python、c++接口训练网络和预测图片