Caffe源码
来源:互联网 发布:ubuntu 拼音 编辑:程序博客网 时间:2024/05/06 01:02
Caffe源码 - ImageDataLayer
Caffe 官方提供的直接从 image 文件读取图像数据及对应label.
# include \<image_data_layer.hpp>
其继承关系图:
1. image_data_layer.hpp
公有成员函数:
ImageDataLayer (const LayerParameter ¶m)
DataLayerSetUp (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)
ExactNumBottomBlobs () const // 返回该层的 bottom blobs 数目,如果没有bottom blob,则返回-1.
ExactNumTopBlobs () const // 返回该层的 top blobs 数目, 如果没有 top blob,则返回-1.
protected成员函数:
可以被派生类对象访问,不能被用户代码(类外)访问.
ShuffleImages ()
load_batch (Batch< Dtype > *batch)
Protected Attributes:
prefetch_rng_
lines_
lines_id_
2. image_data_layer.cpp
#ifdef USE_OPENCV#include <opencv2/core/core.hpp>#include <fstream> // NOLINT(readability/streams)#include <iostream> // NOLINT(readability/streams)#include <string>#include <utility>#include <vector>#include "caffe/data_transformer.hpp"#include "caffe/layers/base_data_layer.hpp"#include "caffe/layers/image_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>ImageDataLayer<Dtype>::~ImageDataLayer<Dtype>() { this->StopInternalThread();}template <typename Dtype>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."; // Read the file with filenames and labels const string& source = this->layer_param_.image_data_param().source(); LOG(INFO) << "Opening file " << source; std::ifstream infile(source.c_str()); string line; size_t pos; int label; while (std::getline(infile, line)) { pos = line.find_last_of(' '); label = atoi(line.substr(pos + 1).c_str()); lines_.push_back(std::make_pair(line.substr(0, pos), label)); } CHECK(!lines_.empty()) << "File is empty"; if (this->layer_param_.image_data_param().shuffle()) { // randomly shuffle data // 随机打乱数据顺序 LOG(INFO) << "Shuffling data"; const unsigned int prefetch_rng_seed = caffe_rng_rand(); prefetch_rng_.reset(new Caffe::RNG(prefetch_rng_seed)); ShuffleImages(); } else { if (this->phase_ == TRAIN && Caffe::solver_rank() > 0 && this->layer_param_.image_data_param().rand_skip() == 0) { LOG(WARNING) << "Shuffling or skipping recommended for multi-GPU"; } } LOG(INFO) << "A total of " << lines_.size() << " images."; lines_id_ = 0; // Check if we would need to randomly skip a few data points // 随机跳过部分数据 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; } // Read an image, and use it to initialize the top blob. // 读取图片,并放入 top blob. cv::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; // 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_.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_.size(); ++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 // 数据标签 vector<int> label_shape(1, batch_size); top[1]->Reshape(label_shape); for (int i = 0; i < this->prefetch_.size(); ++i) { this->prefetch_[i]->label_.Reshape(label_shape); }}template <typename Dtype>void ImageDataLayer<Dtype>::ShuffleImages() { caffe::rng_t* prefetch_rng = static_cast<caffe::rng_t*>(prefetch_rng_->generator()); shuffle(lines_.begin(), lines_.end(), prefetch_rng);}// This function is called on prefetch thread // 预读取数据线程template <typename Dtype>void ImageDataLayer<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()); ImageDataParameter image_data_param = this->layer_param_.image_data_param(); const int batch_size = image_data_param.batch_size(); const int new_height = image_data_param.new_height(); const int new_width = image_data_param.new_width(); const bool is_color = image_data_param.is_color(); string root_folder = image_data_param.root_folder(); // Reshape according to the first image of each batch // on single input batches allows for inputs of varying dimension. // 读取图像数据 // 数据维度调整转换 cv::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; // 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 const int lines_size = lines_.size(); for (int item_id = 0; item_id < batch_size; ++item_id) { // get a blob timer.Start(); CHECK_GT(lines_size, lines_id_); cv::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; read_time += timer.MicroSeconds(); timer.Start(); // Apply transformations (mirror, crop...) to the image // 图像处理,如 mirror,crop 等 int offset = batch->data_.offset(item_id); this->transformed_data_.set_cpu_data(prefetch_data + offset); this->data_transformer_->Transform(cv_img, &(this->transformed_data_)); trans_time += timer.MicroSeconds(); prefetch_label[item_id] = lines_[lines_id_].second; // go to the next iter lines_id_++; if (lines_id_ >= lines_size) { // We have reached the end. Restart from the first. DLOG(INFO) << "Restarting data prefetching from start."; lines_id_ = 0; if (this->layer_param_.image_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(ImageDataLayer);REGISTER_LAYER_CLASS(ImageData);} // namespace caffe#endif // USE_OPENCV
3. 数据格式及网络层定义
数据格式为:
# train.txt001.jpg 1002.jpg 2003.jpg 3
网络层定义:
# train_val.prototxtlayer { name: "demo" type: "ImageData" top: "data" top: "label" include { phase: TRAIN } transform_param { scale: 0.00390625 mean_value: 128 } image_data_param { source: "/path/to/train.txt" root_folder: "/path/to/images" new_height: 224 new_width: 224 batch_size: 32 shuffle: true } }
Reference
[1] - caffe::ImageDataLayer
阅读全文
0 0
- caffe 源码
- Caffe源码
- Caffe源码
- Caffe源码
- Caffe源码
- Caffe源码
- Caffe 源码
- 【caffe源码研究】caffe笔记
- Caffe源码解析caffe.cpp
- 【Caffe源码解析】DataLayer
- caffe源码 layer分析
- caffe源码结构
- [caffe] 源码分析
- 如何解读Caffe源码
- caffe 源码导读
- caffe 源码简单剖析
- caffe源码导读系列
- caffe 源码细节
- 【Java学习笔记之二十四】对Java多态性的一点理解
- ChromeDriver 与chrome 版本
- VNC安装
- Ruby Gem命令详解
- ORA-00923: 未找到要求的 FROM 关键字
- Caffe源码
- ubuntu下mysql安装及python操作
- 什么是跨域,跨域解决办法
- 欧几里得空间
- 使用SHFileOperation实现文件的复制,删除
- hnust 1439 可排回文
- C++编译链接
- 好未来提前批面试
- 求平方根