一、前言
在将图像传输到数据层之前,还需要对图像数据进行预处理。主要的工作是将Datum、const vector、cv::Mat&、vector 、Blob*类型的数据转变为Blob型的数据,以及对数据进行减均值、镜像和切割等操作。
二、源码分析
1、TransformationParameter
在开始看源码之前,首先列出protobuf中的transformer参数,这些参数就是要对数据进行的相关变换。
需要注意的是:
减均值的操作在乘以系数之前。
scale是对像素点乘以某个系数;
mirror是镜像;
crop_size是切割图片的尺寸;
meanfile是存储均值的文件;
meanvalue是存储均值的容器;
后面则是多颜色通道的数据。
message TransformationParameter {
// For data pre-processing, we can do simple scaling and subtracting the
// data mean, if provided. Note that the mean subtraction is always carried
// out before scaling.
optional float scale = 1 [default = 1];
// Specify if we want to randomly mirror data.
optional bool mirror = 2 [default = false];
// Specify if we would like to randomly crop an image.
optional uint32 crop_size = 3 [default = 0];
// mean_file and mean_value cannot be specified at the same time
optional string mean_file = 4;
// if specified can be repeated once (would substract it from all the channels)
// or can be repeated the same number of times as channels
// (would subtract them from the corresponding channel)
repeated float mean_value = 5;
// Force the decoded image to have 3 color channels.
optional bool force_color = 6 [default = false];
// Force the decoded image to have 1 color channels.
optional bool force_gray = 7 [default = false];
}
2、成员变量
TransformationParameter param_;//protobuf参数
shared_ptr<Caffe::RNG> rng_;//随机数发生器
Phase phase_;
Blob<Dtype> data_mean_;//数据均值
vector<Dtype> mean_values_;
3、构造函数
template<typename Dtype>
DataTransformer<Dtype>::DataTransformer(const TransformationParameter& param,
Phase phase)
: param_(param), phase_(phase) {
if (param_.has_mean_file()) {
CHECK_EQ(param_.mean_value_size(), 0) <<
"Cannot specify mean_file and mean_value at the same time";
const string& mean_file = param.mean_file();
if (Caffe::root_solver()) {
LOG(INFO) << "Loading mean file from: " << mean_file;
}
BlobProto blob_proto;
ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto);//从均值文件中读取均值信息到blob_proto中
data_mean_.FromProto(blob_proto);
}
if (param_.mean_value_size() > 0) {
CHECK(param_.has_mean_file() == false) <<
"Cannot specify mean_file and mean_value at the same time";
for (int c = 0; c < param_.mean_value_size(); ++c) {
mean_values_.push_back(param_.mean_value(c));//对不同的blob有不同的均值处理
}
}
}
4、通用Transform转换函数
通用的转换函数,datum是源数据,Dtype* transformed_data是被转换后的数据。后面的Transform重载函数都是通过调用该函数进行处理的,每个重载函数根据参数进行不同的预处理而已。
template<typename Dtype>
void DataTransformer<Dtype>::Transform(const Datum& datum, Dtype* transformed_data)
a、切割处理
只有在训练的时候是随机切割的,这样做的好处是增大样本量,减少过拟合。
在测试的时候,切割是固定的。
int height = datum_height;
int width = datum_width;
int h_off = 0;
int w_off = 0;
if (crop_size) {
height = crop_size;
width = crop_size;
// We only do random crop when we do training.
if (phase_ == TRAIN) {
h_off = Rand(datum_height - crop_size + 1);
w_off = Rand(datum_width - crop_size + 1);
} else {
h_off = (datum_height - crop_size) / 2;
w_off = (datum_width - crop_size) / 2;
}
}
b、镜像
Dtype datum_element;
int top_index, data_index;
for (int c = 0; c < datum_channels; ++c) {
for (int h = 0; h < height; ++h) {
for (int w = 0; w < width; ++w) {
data_index = (c * datum_height + h_off + h) * datum_width + w_off + w;//获取转换数据的坐标
if (do_mirror) {
top_index = (c * height + h) * width + (width - 1 - w);//因为是行优先,所以在width上进行镜像处理了。
} else {
top_index = (c * height + h) * width + w;
}
if (has_uint8) {//是否进行unit8转换
datum_element =
static_cast<Dtype>(static_cast<uint8_t>(data[data_index]));
} else {
datum_element = datum.float_data(data_index);
}
c、减均值,乘系数
if (has_mean_file) {
transformed_data[top_index] =
(datum_element - mean[data_index]) * scale;//减去均值,然后乘以系数
} else {
if (has_mean_values) {
transformed_data[top_index] =
(datum_element - mean_values_[c]) * scale;
} else {
transformed_data[top_index] = datum_element * scale;
}
5、目标转换类型为Blob型指针的Transform转换函数
template<typename Dtype>
void DataTransformer<Dtype>::Transform(const Datum& datum,Blob<Dtype>* transformed_blob) {
// datum是经过编码的数据,则需要先解码
if (datum.encoded()) {
#ifdef USE_OPENCV
//是否使用opencv库的图像数据
CHECK(!(param_.force_color() && param_.force_gray()))
<< "cannot set both force_color and force_gray";
cv::Mat cv_img;
if (param_.force_color() || param_.force_gray()) {
// If force_color then decode in color otherwise decode in gray.
cv_img = DecodeDatumToCVMat(datum, param_.force_color());
} else {
cv_img = DecodeDatumToCVMatNative(datum);
}
// Transform the cv::image into blob.
return Transform(cv_img, transformed_blob);//调用转换mat型数据的函数
#else
LOG(FATAL) << "Encoded datum requires OpenCV; compile with USE_OPENCV.";
#endif // USE_OPENCV
} else {
if (param_.force_color() || param_.force_gray()) {
LOG(ERROR) << "force_color and force_gray only for encoded datum";
}
}
const int crop_size = param_.crop_size();
const int datum_channels = datum.channels();
const int datum_height = datum.height();
const int datum_width = datum.width();
// Check dimensions.
const int channels = transformed_blob->channels();
const int height = transformed_blob->height();
const int width = transformed_blob->width();
const int num = transformed_blob->num();
CHECK_EQ(channels, datum_channels);
CHECK_LE(height, datum_height);
CHECK_LE(width, datum_width);
CHECK_GE(num, 1);
if (crop_size) {
CHECK_EQ(crop_size, height);
CHECK_EQ(crop_size, width);
} else {
CHECK_EQ(datum_height, height);
CHECK_EQ(datum_width, width);
}
Dtype* transformed_data = transformed_blob->mutable_cpu_data();
Transform(datum, transformed_data);//调用通用函数
}
template<typename Dtype>
void DataTransformer<Dtype>::Transform(const vector<Datum> & datum_vector,Blob<Dtype>* transformed_blob) {
const int datum_num = datum_vector.size();
const int num = transformed_blob->num();
const int channels = transformed_blob->channels();
const int height = transformed_blob->height();
const int width = transformed_blob->width();
CHECK_GT(datum_num, 0) << "There is no datum to add";
CHECK_LE(datum_num, num) <<
"The size of datum_vector must be no greater than transformed_blob->num()";
Blob<Dtype> uni_blob(1, channels, height, width);//新建的Blob中只有一个batch的图像数据
for (int item_id = 0; item_id < datum_num; ++item_id) {
int offset = transformed_blob->offset(item_id);//根据偏移量来放置数据
uni_blob.set_cpu_data(transformed_blob->mutable_cpu_data() + offset);//熟悉的set_cpu_data用来初始化新建batch
Transform(datum_vector[item_id], &uni_blob);//对于单独的数据仍然调用单独转换的函数,再进一步调用通用转换函数
}
}
6、对输入为Blob*的数据进行转换的重载函数
template<typename Dtype>
void DataTransformer<Dtype>::Transform(Blob<Dtype>* input_blob,
Blob<Dtype>* transformed_blob) {
const int crop_size = param_.crop_size();//切割尺寸
const int input_num = input_blob->num();//batch_size
const int input_channels = input_blob->channels();//通道数
const int input_height = input_blob->height();
const int input_width = input_blob->width();
if (transformed_blob->count() == 0) {
// Initialize transformed_blob with the right shape.
if (crop_size) {
transformed_blob->Reshape(input_num, input_channels,crop_size, crop_size);//调用Blob的reshape进行切割处理,更新维度信息
} else {
transformed_blob->Reshape(input_num, input_channels,input_height, input_width);
}
}
const int num = transformed_blob->num();
const int channels = transformed_blob->channels();
const int height = transformed_blob->height();
const int width = transformed_blob->width();
const int size = transformed_blob->count();
CHECK_LE(input_num, num);
CHECK_EQ(input_channels, channels);
CHECK_GE(input_height, height);
CHECK_GE(input_width, width);//例行检查
const Dtype scale = param_.scale();
const bool do_mirror = param_.mirror() && Rand(2);
const bool has_mean_file = param_.has_mean_file();
const bool has_mean_values = mean_values_.size() > 0;
int h_off = 0;
int w_off = 0;
if (crop_size) {
CHECK_EQ(crop_size, height);
CHECK_EQ(crop_size, width);
// We only do random crop when we do training.
if (phase_ == TRAIN) {
h_off = Rand(input_height - crop_size + 1);
w_off = Rand(input_width - crop_size + 1);
} else {
h_off = (input_height - crop_size) / 2;
w_off = (input_width - crop_size) / 2;
}
} else {
CHECK_EQ(input_height, height);
CHECK_EQ(input_width, width);
}
Dtype* input_data = input_blob->mutable_cpu_data();
if (has_mean_file) {
CHECK_EQ(input_channels, data_mean_.channels());
CHECK_EQ(input_height, data_mean_.height());
CHECK_EQ(input_width, data_mean_.width());
for (int n = 0; n < input_num; ++n) {//本批次的数据全部进行减均值的计算
int offset = input_blob->offset(n);
caffe_sub(data_mean_.count(), input_data + offset,data_mean_.cpu_data(), input_data + offset);//减均值公式:input_data + offset=input_data + offset-data_mean_.cpu_data()
}
}
if (has_mean_values) {
CHECK(mean_values_.size() == 1 || mean_values_.size() == input_channels) <<
"Specify either 1 mean_value or as many as channels: " << input_channels;
if (mean_values_.size() == 1) {
caffe_add_scalar(input_blob->count(), -(mean_values_[0]), input_data);
} else {
for (int n = 0; n < input_num; ++n) {
for (int c = 0; c < input_channels; ++c) {
int offset = input_blob->offset(n, c);
caffe_add_scalar(input_height * input_width, -(mean_values_[c]),
input_data + offset);//如果均值容器内的元素大于一,说明每个图像数据的均值不一样,需要单独进行计算
}
}
}
}
Dtype* transformed_data = transformed_blob->mutable_cpu_data();
for (int n = 0; n < input_num; ++n) {
int top_index_n = n * channels;
int data_index_n = n * channels;
for (int c = 0; c < channels; ++c) {
int top_index_c = (top_index_n + c) * height;
int data_index_c = (data_index_n + c) * input_height + h_off;
for (int h = 0; h < height; ++h) {
int top_index_h = (top_index_c + h) * width;
int data_index_h = (data_index_c + h) * input_width + w_off;
if (do_mirror) {
int top_index_w = top_index_h + width - 1;//偏移坐标的计算
for (int w = 0; w < width; ++w) {
transformed_data[top_index_w-w] = input_data[data_index_h + w];//镜像,仍然是行优先
}
} else {
for (int w = 0; w < width; ++w) {
transformed_data[top_index_h + w] = input_data[data_index_h + w];
}
}
}
}
}
if (scale != Dtype(1)) {
DLOG(INFO) << "Scale: " << scale;
caffe_scal(size, scale, transformed_data);
}
}
7、推断Blob形状的重载函数
重载函数的方式与上如出一辙,都是在对特殊数据的预处理后调用通用函数进行实质变换。
template<typename Dtype>
vector<int> DataTransformer<Dtype>::InferBlobShape(const Datum& datum) {
if (datum.encoded()) {//如果使用opencv先将其转换为Blob数据类型
#ifdef USE_OPENCV
CHECK(!(param_.force_color() && param_.force_gray()))
<< "cannot set both force_color and force_gray";
cv::Mat cv_img;
if (param_.force_color() || param_.force_gray()) {
// If force_color then decode in color otherwise decode in gray.
cv_img = DecodeDatumToCVMat(datum, param_.force_color());
} else {
cv_img = DecodeDatumToCVMatNative(datum);
}
// InferBlobShape using the cv::image.
return InferBlobShape(cv_img);
#else
LOG(FATAL) << "Encoded datum requires OpenCV; compile with USE_OPENCV.";
#endif // USE_OPENCV
}
//否则直接复制得到其形状
const int crop_size = param_.crop_size();
const int datum_channels = datum.channels();
const int datum_height = datum.height();
const int datum_width = datum.width();
// Check dimensions.
CHECK_GT(datum_channels, 0);
CHECK_GE(datum_height, crop_size);
CHECK_GE(datum_width, crop_size);
// Build BlobShape.
vector<int> shape(4);
shape[0] = 1;
shape[1] = datum_channels;
shape[2] = (crop_size)? crop_size: datum_height;
shape[3] = (crop_size)? crop_size: datum_width;
return shape;
}
8、随机数发生器
template <typename Dtype>
void DataTransformer<Dtype>::InitRand() {
const bool needs_rand = param_.mirror() ||
(phase_ == TRAIN && param_.crop_size());
if (needs_rand) {
const unsigned int rng_seed = caffe_rng_rand();
rng_.reset(new Caffe::RNG(rng_seed));
} else {
rng_.reset();初始化全局的随机数发生器,智能指针的reset()函数
}
}
template <typename Dtype>
int DataTransformer<Dtype>::Rand(int n) {
CHECK(rng_);
CHECK_GT(n, 0);
caffe::rng_t* rng =
static_cast<caffe::rng_t*>(rng_->generator());
return ((*rng)() % n);//调用随机数发生器
}
三、总结
在完成了数据的维度的变换和减均值,镜像等操作后,数据们终于可以进入到神经网络的身体内了……….