- 目标
修改mnist的输入层,以图片《digits.png》作为数据源。
2 操作步骤
2.1 创建新定义的头文件/opt/caffe-master/include/caffe/layers/my_data_layer.hpp
重新Layer名的方法:virtual inline const char* type() const {return “MyData”;}
#ifndef CAFFE_MY_DATA_LAYER_HPP_
#define CAFFE_MY_DATA_LAYER_HPP_
#include <string>
#include <utility>
#include <vector>
#include <algorithm> // std::random_shuffle
#include <vector> // std::vector
#include <ctime> // std::time
#include "caffe/blob.hpp"
#include "caffe/data_transformer.hpp"
#include "caffe/internal_thread.hpp"
#include "caffe/layer.hpp"
#include "caffe/layers/base_data_layer.hpp"
#include "caffe/proto/caffe.pb.h"
namespace caffe {
template <typename Dtype>
class MyDataLayer : public BasePrefetchingDataLayer<Dtype> {
public:
explicit MyDataLayer(const LayerParameter& param)
: BasePrefetchingDataLayer<Dtype>(param){}
virtual ~MyDataLayer();
virtual void DataLayerSetUp(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top);
virtual inline const char* type() const { return "MyData";}
virtual inline int ExactNumBottomBlobs() const { return 0; }
virtual inline int ExactNumTopBlobs() const { return 2; }
protected:
shared_ptr<Caffe::RNG> prefetch_rng_;
virtual void ShuffleImages();
virtual void load_batch(Batch<Dtype>* batch);
inline cv::Mat get_one_sample(cv::Mat whole_img,int pos_x,int pos_y,int width,int height){
return source_image_(cv::Rect(pos_x,pos_y,width,height)).clone();
}
vector<std::pair<cv::Mat, int> > samples_;
int lines_id_;
string image_address_;
int start_col_;
int end_col_;
int sample_width_;
int sample_height_;
cv::Mat source_image_;
};
} // namespace caffe
#endif // CAFFE_MY_DATA_LAYER_HPP_
2.2 创建新定义数据层文件/opt/caffe-master/src/caffe/layers/my_data_layer.cpp
重写LayerSetUp,ShuffleImage,load_batch。
#ifdef USE_OPENCV
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <fstream> // NOLINT(readability/streams)
#include <iostream> // NOLINT(readability/streams)
#include <string>
#include <utility>
#include <vector>
#include <stdio.h>
#include "caffe/data_transformer.hpp"
#include "caffe/layers/base_data_layer.hpp"
#include "caffe/layers/my_data_layer.hpp"
#include "caffe/util/benchmark.hpp"
#include "caffe/util/io.hpp"
#include "caffe/util/math_functions.hpp"
#include "caffe/util/rng.hpp"
namespace caffe {
template <typename Dtype>
MyDataLayer<Dtype>::~MyDataLayer<Dtype>() {
this->StopInternalThread();
}
template <typename Dtype>
void MyDataLayer<Dtype>::DataLayerSetUp(const vector<Blob<Dtype>*>& bottom,const vector<Blob<Dtype>*>& top){
// Init private variables.
image_address_ = this->layer_param_.my_data_param().image_address();
start_col_= this->layer_param_.my_data_param().start_col();
end_col_ = this->layer_param_.my_data_param().end_col();
sample_width_ = this->layer_param_.my_data_param().sample_width();
sample_height_= this->layer_param_.my_data_param().sample_height();
lines_id_ = 0;
int label,x,y;
cv::Mat image;
source_image_ = cv::imread(image_address_);
for(int i=0 ; i< 50 ; i++){
label = (int)(i/5);
for(int j=start_col_ ; j<end_col_ ; j++){
y=20*i;
x=20*j;
image = get_one_sample(source_image_,x,y,20,20);
samples_.push_back(std::make_pair(image,label));
}
}
CHECK(!samples_.empty()) << "Data is empty";
// Shuffle images
if(this->layer_param_.my_data_param().shuffle()){
LOG(INFO) << "Shuffling data";
ShuffleImages();
}
// Save images
if(this->layer_param_.my_data_param().is_save()){
LOG(INFO) << "Saving images ";
for(int i=0;i<samples_.size();i++){
string save_folder = this->layer_param_.my_data_param().save_folder();
char img_name[128];
sprintf(img_name,"%s/%d.jpg",save_folder.c_str(),i);
cv::imwrite(img_name,samples_[i].first);
}
}
// Read an image, and use it to initialize the top blob
cv::Mat cv_img = samples_[lines_id_].first;
CHECK(cv_img.data) << "Could not load first image";
// Use data_transformer to infer the expected blob shape from a cv_image
vector<int> top_shape = this->data_transformer_->InferBlobShape(cv_img);
this->transformed_data_.Reshape(top_shape);
//Reshape prefetch_data and top[0] according to the batch_size.
const int batch_size = this->layer_param_.my_data_param().batch_size();
top_shape[0] = batch_size;
for(int i=0;i<this->PREFETCH_COUNT;++i){
this->prefetch_[i].data_.Reshape(top_shape);
}
top[0]->Reshape(top_shape);
LOG(INFO) << "output data size: " << top[0]->num() << "," << top[0]->channels() << "," << top[0]->height() << "," << top[0]->width();
// label
vector<int> label_shape(1,batch_size);
top[1]->Reshape(label_shape);
for(int i=0;i<this->PREFETCH_COUNT;++i){
this->prefetch_[i].label_.Reshape(label_shape);
}
}
template <typename Dtype>
void MyDataLayer<Dtype>::ShuffleImages(){
std::srand ( unsigned ( std::time(0) ) );
std::random_shuffle(samples_.begin(),samples_.end());
}
template <typename Dtype>
void MyDataLayer<Dtype>::load_batch(Batch<Dtype>* batch){
CPUTimer batch_timer;
batch_timer.Start();
double read_time = 0;
double trans_time = 0;
CPUTimer timer;
CHECK(batch->data_.count());
CHECK(this->transformed_data_.count());
MyDataParameter my_data_param = this-> layer_param_.my_data_param();
// Get batch size
const int batch_size = my_data_param.batch_size();
// Reshape according to the first image of each batch
// on single input batches allows for inputs of varying dimension
cv::Mat cv_img = samples_[lines_id_].first;
CHECK(cv_img.data) << "Could not load "<<lines_id_<<" sample";
// Use data_transformer to infer the expected blob shape from a cv_img
vector<int> top_shape = this->data_transformer_->InferBlobShape(cv_img);
this->transformed_data_.Reshape(top_shape);
// Reshape batch according to the batch_size
top_shape[0] = batch_size;
batch->data_.Reshape(top_shape);
Dtype* prefetch_data = batch->data_.mutable_cpu_data();
Dtype* prefetch_label= batch->label_.mutable_cpu_data();
// datum scales
int samples_size = samples_.size();
for(int item_id=0;item_id<batch_size;++item_id){
// get a blob
timer.Start();
CHECK_GT(samples_size, lines_id_);
cv::Mat sample = samples_[lines_id_].first;
CHECK(sample.data) << "Could not load "<<lines_id_<<" sample";
read_time += timer.MicroSeconds();
timer.Start();
// apply transformations to the image
int offset = batch->data_.offset(item_id);
this->transformed_data_.set_cpu_data(prefetch_data + offset);
this->data_transformer_->Transform(sample,&(this->transformed_data_));
trans_time += timer.MicroSeconds();
prefetch_label[item_id] = samples_[lines_id_].second;
// got the the next iter
lines_id_++;
if(lines_id_>=samples_size){
// We have reached the end. restart from the first.
DLOG(INFO) << "Restarting data prefetching from start.";
lines_id_=0;
if(my_data_param.shuffle()){
ShuffleImages();
}
}
}
batch_timer.Stop();
DLOG(INFO) << "Prefetch batch: " << batch_timer.MilliSeconds() << " ms.";
DLOG(INFO) << " Read time: " << read_time / 1000 << " ms.";
DLOG(INFO) << "Transform time: " << trans_time / 1000 << " ms.";
}
INSTANTIATE_CLASS(MyDataLayer);
REGISTER_LAYER_CLASS(MyData);
} // namespaces caffe
#endif // USE_OPENCV
2.3 在《caffe.porto》中注册数据层
备份文件《/opt/caffe-master/src/caffe/proto/caffe.porto》为《caffe_backup.proto》
在406行加入:
// 注册新的数据层,保险起见,设为150
optional MyDataParameter my_data_param = 150;
在《caffe.porto》中410行加入:
// 定义注册数据层的参数
// to infer image data
message MyDataParameter{
//数据源图片《digits.png》的地址
optional string image_address = 1;
// Start column for calculation
// 训练和测试用的起始列
optional int32 start_col = 2;
// 训练和测试用的结束列
optional int32 end_col = 3;
// Height of each image
optional int32 sample_height = 4 [default = 0];
// Width of each image
optional int32 sample_width = 5 [default = 0];
// Shuffle or not
optional bool shuffle = 6;
// Batch size for each computing
optional int32 batch_size = 7;
// Gray or color (equals to single channel or 3 channels)
optional bool is_color = 8 [default = false];
// Save the image seperated from the image address or not
optional bool is_save = 9 [default = false];
// If save, use this save folder
optional string save_folder = 10;
}
在1323行加入:
// My new data parameter
optional MyDataParameter my_data_param = 50;
2.4 测试
备份文件《/opt/caffe-master/examples/mnist/lenet_train_test.prototxt》为《lenet_train_test_backup.prototxt》
name: "LeNet"
layer {
name: "mnist"
type: "MyData"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
scale: 0.00390625
}
my_data_param {
image_address: "/opt/caffe-master/examples/mnist/Temp/digits.png"
batch_size: 64
start_col:0
end_col:70
shuffle:true
sample_width:20
sample_height:20
is_save:false
save_folder: "/opt/caffe-master/examples/mnist/Temp/img"
}
}
layer {
name: "mnist"
type: "MyData"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
scale: 0.00390625
}
my_data_param {
image_address: "/opt/caffe-master/examples/mnist/Temp/digits.png"
batch_size:32
start_col:70
end_col:100
sample_width:20
sample_height:20
shuffle:true
}
}
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"
}
同样,备份《/opt/caffe-master/examples/mnist/lenet_solver.prototxt》为《lenet_solver_backup.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: 50
# Carry out testing every 500 training iterations.
test_interval: 200
# 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: 200
# The maximum number of iterations
max_iter: 1000
# snapshot intermediate results
snapshot: 500
snapshot_prefix: "examples/mnist/lenet"
# solver mode: CPU or GPU
solver_mode: CPU
重新编译
$ cd /opt/caffe-master
$ cd build
/opt/caffe−master/build sudo rm -rf *
$ cmake -D CMAKE_BUILD_TYPE=RELEASE \
-D CMAKE_INSTALL_PREFIX=/usr/local \
-D INSTALL_C_EXAMPLES=ON \
-D INSTALL_PYTHON_EXAMPLES=ON \
-D WITH_TBB=ON \
-D WITH_V4L=ON \
-D WITH_QT=OFF \
-D WITH_OPENGL=ON \
-D OPENCV_EXTRA_MODULES_PATH=../../opencv_contrib/modules \
-D CPU_ONLY=ON \
-D BUILD_EXAMPLES=ON ..
/opt/caffe-master/build$ sudo make all
新建文件mydata.sh
#!/usr/bin/env sh
set -e
./build/tools/caffe train --solver=examples/mnist/lenet_solver.prototxt $@
运行测试文件mydata.sh
/opt/caffe-master$ ./examples/mnist/mydata.sh
参考资料:
caffe总结之自定义数据输入层
http://blog.csdn.net/u013289254/article/details/70432304
Caffe添加新层
http://blog.csdn.net/shuzfan/article/details/51322976
Caffe自定义数据读取
http://www.meltycriss.com/2016/07/04/caffe_1_layer/
Caffe数据层参数
http://www.cnblogs.com/denny402/p/5070928.html
Caffe实现多标签输入
http://www.tk4479.net/AMDS123/article/details/62423987
梳理caffe代码image_data_layer、data_layer、window_data_layer(七)
http://blog.csdn.net/langb2014/article/details/50998135
其他相关网站
http://www.miaoerduo.com/