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