Caffe框架,了解三个文件

不知道从什么时候开始，Deep Learning成为了各个领域研究的热点，也不知道从什么时候开始，2015CVPR的文章出现了很多Deep Learning的文章，更不知道从什么时候开始，三维重建各个研究方向也要被Deep Learning攻破了。

从这个时候开始，我要开始学习Deep Learning了，因为我研究的方向已然被攻破！

以上是引言部分，下面开始介绍本文的内容。

我前段时间已经配置好Caffe这个框架，现在来摸索一下。本文分为两个部分，第一部分说明学习Caffe框架需要重点记住那些文件；第二部分使用Caffe框架对MNIST数据集进行训练学习。

一. Caffe框架文件

以‘$root’作为Caffe的主目录，以MNIST数据集训练学习作为例子，我觉得只要掌握三个文件就够了：

1. train_lenet.sh $root /examples/mnist/train_lenet.sh

#!/usr/bin/env sh

./build/tools/caffe train --solver=examples/mnist/lenet_solver.prototxt

使用caffe调用lenet_solver.prototxt进行train，’.prototxt’是一种文本文件，这里需要知道的是lenet_solver.prototxt是CNN网络学习的核心，下面我们将要学习它。

2. lenet_solver.prototxt $root /examples/mnist/lenet_solver.prototxt

# 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

net: “examples/mnist/lenet_train_test.prototxt”是网络结构设置，其他部分是参数设置，看注释就很明白了。

3. lenet_train_test.prototxt $root /examples/mnist/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"
}

这是各层网络的设置，看内容就知道了。需要注意的是，include {phase: TEST}是指测试网络，未标明的是train和test都可以使用。

二. MNIST数据集进行训练学习

cd $root
./data/mnist/get_mnist.sh
./examples/mnist/create_mnist.sh
./examples/mnist/train_lenet.sh

get_mnist.sh下载MNIST数据集

create_mnist.sh将MNIST数据转换为lmdb格式的数据

在网络中的数据存储和操作是以Blobs形式

train_lenet.sh训练



参考：http://caffe.berkeleyvision.org/gathered/examples/mnist.html