轉載請注明出處,樓燚(yì)航的blog,http://home.cnblogs.com/louyihang-loves-baiyan/
data_layer應該是網絡的最底層,主要是將數據送給blob進入到net中,在data_layer中存在多個跟data_layer相關的類
- BaseDataLayer
- BasePrefetchingDataLayer
- DataLayer
- DummyDataLayer
- HDF5DataLayer
- HDF5OutputLayer
- ImageDataLayer
- MemoryDataLayer
- WindowDataLayer
- Batch
這里首先說明一下這幾個類之間的區別。
首先Layer是基類,這個之前就已經提到過了。其次看HDF5相關的類有兩個,一個是HDF5DataLayer,另一個是HDF5OutputLayer,主要是基于HDF5數據格式的讀取和存儲
留意到這個data_layer的頭文件還include了不少頭文件
#include <string>
#include <utility>
#include <vector>
#include "hdf5.h"#include "caffe/blob.hpp"
#include "caffe/common.hpp"
#include "caffe/data_reader.hpp"
#include "caffe/data_transformer.hpp"
#include "caffe/filler.hpp"
#include "caffe/internal_thread.hpp"
#include "caffe/layer.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/util/blocking_queue.hpp"
#include "caffe/util/db.hpp"
hdf5就是之前說到的一種主要用于科學數據記錄、能自我描述的數據格式。
還有幾個跟data相關的頭文件比如data_read.hpp,data_transformer.hpp
其中data_reader主要是負責數據的讀取,傳送到data layer中。并且對于每一個source,都會開一一起獨立的reading thread讀取線程,幾十有多個solver在并行的跑。比如在多GPU訓練的時候,可以保證對于數據庫的讀取是順序的
data_transformer.hpp里面的DataTransformer這個類,這個類我們要關注一下,這個類主要能對input data 執一些預處理操作,比如縮放、鏡像、減去均值。同時還支持一些隨機的操作。
其核心的函數如下,這里總共有5個常在的Transform函數,其中所有函數的第二部分是相同的,都是一個目標blob,而輸入根據輸入的情況可以有所選擇,可以是blob,也可以是opencv的mat 結構,或者proto中定義的datum結構。
void Transform(const Datum& datum, Blob<Dtype>* transformed_blob);
void Transform(const vector<Datum> & datum_vector, Blob<Dtype>* transformed_blob);
void Transform(const vector<cv::Mat> & mat_vector, Blob<Dtype>* transformed_blob);
void Transform(const cv::Mat& cv_img, Blob<Dtype>* transformed_blob);
void Transform(Blob<Dtype>* input_blob, Blob<Dtype>* transformed_blob);
TransformationParameter是該類構造器中需要傳入的一些變形參數,相關的操作定義在proto中,摘錄如下,可以看到總共有sacle,mirror,crop_size,mean_file,mean_value,force_color,force_grey共7個相關操作
message TransformationParameter {optional float scale = 1 [default = 1];optional bool mirror = 2 [default = false];optional uint32 crop_size = 3 [default = 0];optional string mean_file = 4;repeated float mean_value = 5;optional bool force_color = 6 [default = false];optional bool force_gray = 7 [default = false];
}
首先對于dat_layer,里面根據繼承關系最后的幾個子類分別是ImageDataLayer,DataLayer,WindowDataLayer,MemoryDataLayer,HDF5以及Dummy這里暫時先不做分析。
其實最重要的就是類面的layerSetup.首先我們來看DataLayer的DataLayerSetUp
void DataLayer<Dtype>::DataLayerSetUp(const vector<Blob<Dtype>*>& bottom,const vector<Blob<Dtype>*>& top) {const int batch_size = this->layer_param_.data_param().batch_size();//獲得相應的datum,用來初始化top blobDatum& datum = *(reader_.full().peek());//使用data_transformer 來計算根據datum的期望blob的shapevector<int> top_shape = this->data_transformer_->InferBlobShape(datum);this->transformed_data_.Reshape(top_shape);//首先reshape top[0],再根據batch的大小進行預取top_shape[0] = batch_size;top[0]->Reshape(top_shape);for (int i = 0; i < this->PREFETCH_COUNT; ++i) {this->prefetch_[i].data_.Reshape(top_shape);}LOG(INFO) << "output data size: " << top[0]->num() << ","<< top[0]->channels() << "," << top[0]->height() << ","<< top[0]->width();// 同樣reshape label的blob的shapeif (this->output_labels_) {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);}}
}
MemoryDataLayer
void MemoryDataLayer<Dtype>::DataLayerSetUp(const vector<Blob<Dtype>*>& bottom,const vector<Blob<Dtype>*>& top) {//直接通過memory_data_param類設置layer的相關參數batch_size_ = this->layer_param_.memory_data_param().batch_size();channels_ = this->layer_param_.memory_data_param().channels();height_ = this->layer_param_.memory_data_param().height();width_ = this->layer_param_.memory_data_param().width();size_ = channels_ * height_ * width_;CHECK_GT(batch_size_ * size_, 0) <<"batch_size, channels, height, and width must be specified and"" positive in memory_data_param";//這里跟datalayer一樣都是先設置top[0],然后對label進行reshapevector<int> label_shape(1, batch_size_);top[0]->Reshape(batch_size_, channels_, height_, width_);top[1]->Reshape(label_shape);added_data_.Reshape(batch_size_, channels_, height_, width_);added_label_.Reshape(label_shape);data_ = NULL;labels_ = NULL;added_data_.cpu_data();added_label_.cpu_data();
}
ImageDataLayer,它的DataLayerSetUP函數
void ImageDataLayer<Dtype>::DataLayerSetUp(const vector<Blob<Dtype>*>& bottom,const vector<Blob<Dtype>*>& top) {const int new_height = this->layer_param_.image_data_param().new_height();const int new_width = this->layer_param_.image_data_param().new_width();const bool is_color = this->layer_param_.image_data_param().is_color();string root_folder = this->layer_param_.image_data_param().root_folder();CHECK((new_height == 0 && new_width == 0) ||(new_height > 0 && new_width > 0)) << "Current implementation requires ""new_height and new_width to be set at the same time.";//讀取圖像文件和相應的labelconst string& source = this->layer_param_.image_data_param().source();LOG(INFO) << "Opening file " << source;std::ifstream infile(source.c_str());string filename;int label;while (infile >> filename >> label) {lines_.push_back(std::make_pair(filename, label));}if (this->layer_param_.image_data_param().shuffle()) {// randomly shuffle dataLOG(INFO) << "Shuffling data";const unsigned int prefetch_rng_seed = caffe_rng_rand();prefetch_rng_.reset(new Caffe::RNG(prefetch_rng_seed));ShuffleImages();}LOG(INFO) << "A total of " << lines_.size() << " images.";lines_id_ = 0;//check是否需要隨機跳過一些圖像if (this->layer_param_.image_data_param().rand_skip()) {unsigned int skip = caffe_rng_rand() %this->layer_param_.image_data_param().rand_skip();LOG(INFO) << "Skipping first " << skip << " data points.";CHECK_GT(lines_.size(), skip) << "Not enough points to skip";lines_id_ = skip;}//使用Opencv來讀進圖像,然后使用它初始化相應的top blobcv::Mat cv_img = ReadImageToCVMat(root_folder + lines_[lines_id_].first,new_height, new_width, is_color);CHECK(cv_img.data) << "Could not load " << lines_[lines_id_].first;//這里的步驟和上面相同,使用transformer來做reshapevector<int> top_shape = this->data_transformer_->InferBlobShape(cv_img);this->transformed_data_.Reshape(top_shape);//之后部分跟前面差不多,初始化top[0]const int batch_size = this->layer_param_.image_data_param().batch_size();CHECK_GT(batch_size, 0) << "Positive batch size required";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();//reshape labelvector<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);}
}
WindowDataLayer的DataLayerSetUp,這個函數標比較長,我只列出了其中主要的部分,之前的Image相當于是已經剪裁過的一個圖像,也就是說你的目標基本上是充棉了整個畫面,而Window File是用于原始圖的,也就是說有background和object,這個window file 的格式如下
window_file format
repeated:# image_indeximg_path (abs path)channelsheightwidthnum_windowsclass_index overlap x1 y1 x2 y2
//讀取每一個box
int num_windows;
infile >> num_windows;
const float fg_threshold =this->layer_param_.window_data_param().fg_threshold();
const float bg_threshold =this->layer_param_.window_data_param().bg_threshold();
for (int i = 0; i < num_windows; ++i) {int label, x1, y1, x2, y2;float overlap;infile >> label >> overlap >> x1 >> y1 >> x2 >> y2;vector<float> window(WindowDataLayer::NUM);window[WindowDataLayer::IMAGE_INDEX] = image_index;window[WindowDataLayer::LABEL] = label;window[WindowDataLayer::OVERLAP] = overlap;window[WindowDataLayer::X1] = x1;window[WindowDataLayer::Y1] = y1;window[WindowDataLayer::X2] = x2;window[WindowDataLayer::Y2] = y2;// add window to foreground list or background list// read each box
int num_windows;
infile >> num_windows;
const float fg_threshold =this->layer_param_.window_data_param().fg_threshold();
const float bg_threshold =this->layer_param_.window_data_param().bg_threshold();
for (int i = 0; i < num_windows; ++i) {int label, x1, y1, x2, y2;float overlap;infile >> label >> overlap >> x1 >> y1 >> x2 >> y2;vector<float> window(WindowDataLayer::NUM);window[WindowDataLayer::IMAGE_INDEX] = image_index;window[WindowDataLayer::LABEL] = label;window[WindowDataLayer::OVERLAP] = overlap;window[WindowDataLayer::X1] = x1;window[WindowDataLayer::Y1] = y1;window[WindowDataLayer::X2] = x2;window[WindowDataLayer::Y2] = y2;//首先計算得到overlap,根據Overlap與fg_threshold的比較載添加到fg的list中if (overlap >= fg_threshold) {int label = window[WindowDataLayer::LABEL];CHECK_GT(label, 0);fg_windows_.push_back(window);label_hist.insert(std::make_pair(label, 0));label_hist[label]++;} else if (overlap < bg_threshold) {// background window, force label and overlap to 0window[WindowDataLayer::LABEL] = 0;window[WindowDataLayer::OVERLAP] = 0;bg_windows_.push_back(window);label_hist[0]++;}
}
=-if (overlap >= fg_threshold) {int label = window[WindowDataLayer::LABEL];CHECK_GT(label, 0);fg_windows_.push_back(window);label_hist.insert(std::make_pair(label, 0));label_hist[label]++;} else if (overlap < bg_threshold) {//background的label和overlap都是0window[WindowDataLayer::LABEL] = 0;window[WindowDataLayer::OVERLAP] = 0;bg_windows_.push_back(window);label_hist[0]++;}
}..............
for (map<int, int>::iterator it = label_hist.begin();it != label_hist.end(); ++it) {LOG(INFO) << "class " << it->first << " has " << label_hist[it->first]<< " samples";}LOG(INFO) << "Amount of context padding: "<< this->layer_param_.window_data_param().context_pad();LOG(INFO) << "Crop mode: "<< this->layer_param_.window_data_param().crop_mode();//這里之后的步驟就差不多了,同樣是對transform的一些操作const int crop_size = this->transform_param_.crop_size();CHECK_GT(crop_size, 0);const int batch_size = this->layer_param_.window_data_param().batch_size();top[0]->Reshape(batch_size, channels, crop_size, crop_size);for (int i = 0; i < this->PREFETCH_COUNT; ++i)this->prefetch_[i].data_.Reshape(batch_size, channels, crop_size, crop_size);LOG(INFO) << "output data size: " << top[0]->num() << ","<< top[0]->channels() << "," << top[0]->height() << ","<< top[0]->width();// 對label進行reshapevector<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);}//做減均值的操作has_mean_file_ = this->transform_param_.has_mean_file();has_mean_values_ = this->transform_param_.mean_value_size() > 0;if (has_mean_file_) {const string& mean_file =this->transform_param_.mean_file();LOG(INFO) << "Loading mean file from: " << mean_file;BlobProto blob_proto;ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto);data_mean_.FromProto(blob_proto);}if (has_mean_values_) {CHECK(has_mean_file_ == false) <<"Cannot specify mean_file and mean_value at the same time";for (int c = 0; c < this->transform_param_.mean_value_size(); ++c) {mean_values_.push_back(this->transform_param_.mean_value(c));}CHECK(mean_values_.size() == 1 || mean_values_.size() == channels) <<"Specify either 1 mean_value or as many as channels: " << channels;if (channels > 1 && mean_values_.size() == 1) {// Replicate the mean_value for simplicityfor (int c = 1; c < channels; ++c) {mean_values_.push_back(mean_values_[0]);}}}