caffe源码 之 layer类
来源:互联网 发布:融合交换机软件下载 编辑:程序博客网 时间:2024/06/06 20:52
本文主要解析caffe的中层类定义模块文件/src/caffe/layer.hpp layer.cpp,layer是所有层的基类。
综述::layer.hpp定义了layer的基类,其他例如:loss_layer,data_layer,vision_layer都是在这个layer类的基础上继承的,他们分别实现了基类layer中的一些弱函数,下面通过注释记录下我对基类源码的理解:::::
layer.hpp::::::::::::::
#ifndef CAFFE_LAYER_H_#define CAFFE_LAYER_H_#include <algorithm>#include <string>#include <vector>#include "caffe/blob.hpp"#include "caffe/common.hpp"#include "caffe/layer_factory.hpp"#include "caffe/proto/caffe.pb.h"#include "caffe/util/math_functions.hpp"/** Forward declare boost::thread instead of including boost/thread.hpp to avoid a boost/NVCC issues (#1009, #1010) on OSX. */namespace boost { class mutex; }namespace caffe {/** * @brief An interface for the units of computation which can be composed into a * Net. * * Layer%s must implement a Forward function, in which they take their input * (bottom) Blob%s (if any) and compute their output Blob%s (if any). * They may also implement a Backward function, in which they compute the error * gradients with respect to their input Blob%s, given the error gradients with * their output Blob%s. */template <typename Dtype>class Layer { public: /** * You should not implement your own constructor. Any set up code should go * to SetUp(), where the dimensions of the bottom blobs are provided to the * layer. */ explicit Layer(const LayerParameter& param) /*从solver.prototxt文件中传入的网络参数*/ : layer_param_(param), is_shared_(false) { // Set phase and copy blobs (if there are any). phase_ = param.phase(); /*将当前网络是用来测试test还是train的属性值赋值*/ if (layer_param_.blobs_size() > 0) { blobs_.resize(layer_param_.blobs_size()); for (int i = 0; i < layer_param_.blobs_size(); ++i) { blobs_[i].reset(new Blob<Dtype>()); blobs_[i]->FromProto(layer_param_.blobs(i)); /*blobs_ 是一个容器用来存放指向Blob类的智能指针, 这里将protobuf中所有的blobs拷贝到参数blobs_ 所指向缓存*/ } } } virtual ~Layer() {} /*类的析构函数*/ /** * @brief Implements common layer setup functionality. * * @param bottom the preshaped input blobs * @param top * the allocated but unshaped output blobs, to be shaped by Reshape * * Checks that the number of bottom and top blobs is correct. * Calls LayerSetUp to do special layer setup for individual layer types, * followed by Reshape to set up sizes of top blobs and internal buffers. * Sets up the loss weight multiplier blobs for any non-zero loss weights. * This method may not be overridden. */ void SetUp(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) { InitMutex(); CheckBlobCounts(bottom, top); /*检查传入的top与bottom数据的blob是否正确*/ //每层进行具体配置 LayerSetUp(bottom, top); //为了适应输入(bottom)数据的blob的shape的需要,来修改输出(top)数据的blob的shape Reshape(bottom, top); //初始化损失函数中任何与输入(top)blob数据相关的权重 SetLossWeights(top); } /** * @brief Does layer-specific setup: your layer should implement this function * as well as Reshape. * * @param bottom * the preshaped input blobs, whose data fields store the input data for * this layer * @param top * the allocated but unshaped output blobs * * This method should do one-time layer specific setup. This includes reading * and processing relevent parameters from the <code>layer_param_</code>. * Setting up the shapes of top blobs and internal buffers should be done in * <code>Reshape</code>, which will be called before the forward pass to * adjust the top blob sizes. */ /*具体的每层的设置函数,虚函数每层要具体的实现这个函数*/ virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {} /** * @brief Whether a layer should be shared by multiple nets during data * parallelism. By default, all layers except for data layers should * not be shared. data layers should be shared to ensure each worker * solver access data sequentially during data parallelism. */ /*反回并行状态,默认除了data layer层其他层都是关闭的*/ virtual inline bool ShareInParallel() const { return false; } /** @brief Return whether this layer is actually shared by other nets. * If ShareInParallel() is true and using more than one GPU and the * net has TRAIN phase, then this function is expected return true. */ /*在ShareInParallel返回的值表示该层被共享的前提下, 用这个函数来确定返回参数is_shared_来确定当前层是否被多个网络共享*/ inline bool IsShared() const { return is_shared_; } /** @brief Set whether this layer is actually shared by other nets * If ShareInParallel() is true and using more than one GPU and the * net has TRAIN phase, then is_shared should be set true. */ /*在ShareInParallel返回的值表示该层被共享的前提下, 用这个函数来设置参数is_shared_与上面的函数IsShared()相对应*/ inline void SetShared(bool is_shared) { CHECK(ShareInParallel() || !is_shared) << type() << "Layer does not support sharing."; is_shared_ = is_shared; } /** * @brief Adjust the shapes of top blobs and internal buffers to accommodate * the shapes of the bottom blobs. * * @param bottom the input blobs, with the requested input shapes * @param top the top blobs, which should be reshaped as needed * * This method should reshape top blobs as needed according to the shapes * of the bottom (input) blobs, as well as reshaping any internal buffers * and making any other necessary adjustments so that the layer can * accommodate the bottom blobs. */ //为了适应输入(bottom)数据的blob的shape的需要,来修改输出(top)数据的blob的shape virtual void Reshape(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) = 0; /** * @brief Given the bottom blobs, compute the top blobs and the loss. * * @param bottom * the input blobs, whose data fields store the input data for this layer * @param top * the preshaped output blobs, whose data fields will store this layers' * outputs * \return The total loss from the layer. * * The Forward wrapper calls the relevant device wrapper function * (Forward_cpu or Forward_gpu) to compute the top blob values given the * bottom blobs. If the layer has any non-zero loss_weights, the wrapper * then computes and returns the loss. * * Your layer should implement Forward_cpu and (optionally) Forward_gpu. */ /*实现前向传播函数,根据输入数据的blob来计算输出数据的blob,并且计算损失量*/ inline Dtype Forward(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top); /** * @brief Given the top blob error gradients, compute the bottom blob error * gradients. * * @param top * the output blobs, whose diff fields store the gradient of the error * with respect to themselves * @param propagate_down * a vector with equal length to bottom, with each index indicating * whether to propagate the error gradients down to the bottom blob at * the corresponding index * @param bottom * the input blobs, whose diff fields will store the gradient of the error * with respect to themselves after Backward is run * * The Backward wrapper calls the relevant device wrapper function * (Backward_cpu or Backward_gpu) to compute the bottom blob diffs given the * top blob diffs. * * Your layer should implement Backward_cpu and (optionally) Backward_gpu. */ /*实现后向传播函数, 根据输出数据的误差梯度计算输出数据的误差梯度*/ inline void Backward(const vector<Blob<Dtype>*>& top, const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom); /** * @brief Returns the vector of learnable parameter blobs. */ vector<shared_ptr<Blob<Dtype> > >& blobs() { return blobs_; /*返回学习的参数,以blobs的容器保存的*/ } /** * @brief Returns the layer parameter. */ /*返回传入的该层的配置参数*/ const LayerParameter& layer_param() const { return layer_param_; } /** * @brief Writes the layer parameter to a protocol buffer */ /*将层参数写成Protobuffer文件*/ virtual void ToProto(LayerParameter* param, bool write_diff = false); /** * @brief Returns the scalar loss associated with a top blob at a given index. */ /*根据索引返回输出数据相关的损失量*/ inline Dtype loss(const int top_index) const { return (loss_.size() > top_index) ? loss_[top_index] : Dtype(0); } /** * @brief Sets the loss associated with a top blob at a given index. */ /*根据索引设置相关的损失量*/ inline void set_loss(const int top_index, const Dtype value) { if (loss_.size() <= top_index) { loss_.resize(top_index + 1, Dtype(0)); } loss_[top_index] = value; } /** * @brief Returns the layer type. */ /*返回layer的类型,具体的层具体实现*/ virtual inline const char* type() const { return ""; } /** * @brief Returns the exact number of bottom blobs required by the layer, * or -1 if no exact number is required. * * This method should be overridden to return a non-negative value if your * layer expects some exact number of bottom blobs. */ /*返回具体的输入的blobs的个数*/ virtual inline int ExactNumBottomBlobs() const { return -1; } /** * @brief Returns the minimum number of bottom blobs required by the layer, * or -1 if no minimum number is required. * * This method should be overridden to return a non-negative value if your * layer expects some minimum number of bottom blobs. */ /*返回当前层所需的最少输入的blobs数量*/ virtual inline int MinBottomBlobs() const { return -1; } /** * @brief Returns the maximum number of bottom blobs required by the layer, * or -1 if no maximum number is required. * * This method should be overridden to return a non-negative value if your * layer expects some maximum number of bottom blobs. */ /*返回当前层所需的最多的输入的blobs数量*/ virtual inline int MaxBottomBlobs() const { return -1; } /** * @brief Returns the exact number of top blobs required by the layer, * or -1 if no exact number is required. * * This method should be overridden to return a non-negative value if your * layer expects some exact number of top blobs. */ /*返回具体的输出的blobs的个数*/ virtual inline int ExactNumTopBlobs() const { return -1; } /** * @brief Returns the minimum number of top blobs required by the layer, * or -1 if no minimum number is required. * * This method should be overridden to return a non-negative value if your * layer expects some minimum number of top blobs. */ /*返回当前层所需的最少输出的blobs数量*/ virtual inline int MinTopBlobs() const { return -1; } /** * @brief Returns the maximum number of top blobs required by the layer, * or -1 if no maximum number is required. * * This method should be overridden to return a non-negative value if your * layer expects some maximum number of top blobs. */ /*返回当前层所需的最多输出的blobs数量*/ virtual inline int MaxTopBlobs() const { return -1; } /** * @brief Returns true if the layer requires an equal number of bottom and * top blobs. * * This method should be overridden to return true if your layer expects an * equal number of bottom and top blobs. */ /*判断输入与输出的blobs数量是否一致*/ virtual inline bool EqualNumBottomTopBlobs() const { return false; } /** * @brief Return whether "anonymous" top blobs are created automatically * by the layer. * * If this method returns true, Net::Init will create enough "anonymous" top * blobs to fulfill the requirement specified by ExactNumTopBlobs() or * MinTopBlobs(). */ /*如果返回true, Net::Init就会自动创建足够的top blobs来满足 ExactNumTopBlobs()和MinTopBlobs()的需要*/ virtual inline bool AutoTopBlobs() const { return false; } /** * @brief Return whether to allow force_backward for a given bottom blob * index. * * If AllowForceBackward(i) == false, we will ignore the force_backward * setting and backpropagate to blob i only if it needs gradient information * (as is done when force_backward == false). */ /*设置是否强制梯度返回,因为有些层其实不需要梯度信息 */ virtual inline bool AllowForceBackward(const int bottom_index) const { return true; } /** * @brief Specifies whether the layer should compute gradients w.r.t. a * parameter at a particular index given by param_id. * * You can safely ignore false values and always compute gradients * for all parameters, but possibly with wasteful computation. */ /*确定当前层是否应该计算梯度*/ inline bool param_propagate_down(const int param_id) { return (param_propagate_down_.size() > param_id) ? param_propagate_down_[param_id] : false; } /** * @brief Sets whether the layer should compute gradients w.r.t. a * parameter at a particular index given by param_id. */ /*设置当前层是否需要计算梯度*/ inline void set_param_propagate_down(const int param_id, const bool value) { if (param_propagate_down_.size() <= param_id) { param_propagate_down_.resize(param_id + 1, true); } param_propagate_down_[param_id] = value; } protected: /** The protobuf that stores the layer parameters */ LayerParameter layer_param_; //配置的层参数 /** The phase: TRAIN or TEST */ Phase phase_; //当前处在test还是train阶段 /** The vector that stores the learnable parameters as a set of blobs. */ vector<shared_ptr<Blob<Dtype> > > blobs_; //blobs_是一个vector容器,其元素是指向Blob的shared_ptr指针,将可学习的参数存在一组Blob类内 /** Vector indicating whether to compute the diff of each param blob. */ vector<bool> param_propagate_down_; //标识是否为每个参数的blob计算梯度 /** The vector that indicates whether each top blob has a non-zero weight in * the objective function. */ vector<Dtype> loss_; /*标识哪个top blob 有非零的权重*/ /** @brief Using the CPU device, compute the layer output. */ virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) = 0; /*用cpu实现的前向传播函数*/ /** * @brief Using the GPU device, compute the layer output. * Fall back to Forward_cpu() if unavailable. */ virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) { // LOG(WARNING) << "Using CPU code as backup."; return Forward_cpu(bottom, top); /*gpu实现的前向传播函数*/ } /** * @brief Using the CPU device, compute the gradients for any parameters and * for the bottom blobs if propagate_down is true. */ virtual void Backward_cpu(const vector<Blob<Dtype>*>& top, const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) = 0; /*cpu实现后向传播*/ /** * @brief Using the GPU device, compute the gradients for any parameters and * for the bottom blobs if propagate_down is true. * Fall back to Backward_cpu() if unavailable. */ virtual void Backward_gpu(const vector<Blob<Dtype>*>& top, const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) { // LOG(WARNING) << "Using CPU code as backup."; Backward_cpu(top, propagate_down, bottom); /*gpu实现后向传播*/ } /** * Called by the parent Layer's SetUp to check that the number of bottom * and top Blobs provided as input match the expected numbers specified by * the {ExactNum,Min,Max}{Bottom,Top}Blobs() functions. */ /*检查输入与输出的blobs个数是否正确*/ virtual void CheckBlobCounts(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) { if (ExactNumBottomBlobs() >= 0) { CHECK_EQ(ExactNumBottomBlobs(), bottom.size()) << type() << " Layer takes " << ExactNumBottomBlobs() << " bottom blob(s) as input."; } if (MinBottomBlobs() >= 0) { CHECK_LE(MinBottomBlobs(), bottom.size()) << type() << " Layer takes at least " << MinBottomBlobs() << " bottom blob(s) as input."; } if (MaxBottomBlobs() >= 0) { CHECK_GE(MaxBottomBlobs(), bottom.size()) << type() << " Layer takes at most " << MaxBottomBlobs() << " bottom blob(s) as input."; } if (ExactNumTopBlobs() >= 0) { CHECK_EQ(ExactNumTopBlobs(), top.size()) << type() << " Layer produces " << ExactNumTopBlobs() << " top blob(s) as output."; } if (MinTopBlobs() >= 0) { CHECK_LE(MinTopBlobs(), top.size()) << type() << " Layer produces at least " << MinTopBlobs() << " top blob(s) as output."; } if (MaxTopBlobs() >= 0) { CHECK_GE(MaxTopBlobs(), top.size()) << type() << " Layer produces at most " << MaxTopBlobs() << " top blob(s) as output."; } if (EqualNumBottomTopBlobs()) { CHECK_EQ(bottom.size(), top.size()) << type() << " Layer produces one top blob as output for each " << "bottom blob input."; } } /** * Called by SetUp to initialize the weights associated with any top blobs in * the loss function. Store non-zero loss weights in the diff blob. */ /*初始化输出数据的权重*/ inline void SetLossWeights(const vector<Blob<Dtype>*>& top) { const int num_loss_weights = layer_param_.loss_weight_size(); if (num_loss_weights) { CHECK_EQ(top.size(), num_loss_weights) << "loss_weight must be " "unspecified or specified once per top blob."; for (int top_id = 0; top_id < top.size(); ++top_id) { const Dtype loss_weight = layer_param_.loss_weight(top_id); if (loss_weight == Dtype(0)) { continue; } this->set_loss(top_id, loss_weight); const int count = top[top_id]->count(); Dtype* loss_multiplier = top[top_id]->mutable_cpu_diff(); caffe_set(count, loss_weight, loss_multiplier); } } } private: /** Whether this layer is actually shared by other nets*/ bool is_shared_; /*标识该层是否被其他网络共享*/ /** The mutex for sequential forward if this layer is shared */ shared_ptr<boost::mutex> forward_mutex_; /*下面是多线程的一些操作*/ /** Initialize forward_mutex_ */ void InitMutex(); /** Lock forward_mutex_ if this layer is shared */ void Lock(); /** Unlock forward_mutex_ if this layer is shared */ void Unlock(); DISABLE_COPY_AND_ASSIGN(Layer);}; // class Layer// Forward and backward wrappers. You should implement the cpu and// gpu specific implementations instead, and should not change these// functions.template <typename Dtype>inline Dtype Layer<Dtype>::Forward(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) { // Lock during forward to ensure sequential forward Lock(); /*锁住保证按顺序实现前向传播*/ Dtype loss = 0; Reshape(bottom, top); switch (Caffe::mode()) { /*检查传入的运行模式,是只在cpu模式下运行,还是gpu模式下运行*/ case Caffe::CPU: Forward_cpu(bottom, top); /*如果是cpu模式下运行,则调用Forward_cpu计算输入的blobs与loss,不同的layer实现不同*/ for (int top_id = 0; top_id < top.size(); ++top_id) { if (!this->loss(top_id)) { continue; } const int count = top[top_id]->count(); const Dtype* data = top[top_id]->cpu_data(); const Dtype* loss_weights = top[top_id]->cpu_diff(); loss += caffe_cpu_dot(count, data, loss_weights); /*累加每个输出数据的loss*/ } break; case Caffe::GPU: Forward_gpu(bottom, top); /*如果是gpu模式下运行,则调用Forward_gpu计算输入的blobs与loss,不同的layer实现不同*/#ifndef CPU_ONLY for (int top_id = 0; top_id < top.size(); ++top_id) { if (!this->loss(top_id)) { continue; } const int count = top[top_id]->count(); const Dtype* data = top[top_id]->gpu_data(); const Dtype* loss_weights = top[top_id]->gpu_diff(); Dtype blob_loss = 0; caffe_gpu_dot(count, data, loss_weights, &blob_loss);/*累加每个输出数据的loss*/ loss += blob_loss; }#endif break; default: LOG(FATAL) << "Unknown caffe mode."; } Unlock(); return loss;}/*后向传播的实现,根据模式的不同调用不同的实现函数*/template <typename Dtype>inline void Layer<Dtype>::Backward(const vector<Blob<Dtype>*>& top, const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) { switch (Caffe::mode()) { case Caffe::CPU: Backward_cpu(top, propagate_down, bottom); break; case Caffe::GPU: Backward_gpu(top, propagate_down, bottom); break; default: LOG(FATAL) << "Unknown caffe mode."; }}// Serialize LayerParameter to protocol buffer/*将参数保存到protocol缓存*/template <typename Dtype>void Layer<Dtype>::ToProto(LayerParameter* param, bool write_diff) { param->Clear(); param->CopyFrom(layer_param_); param->clear_blobs(); for (int i = 0; i < blobs_.size(); ++i) { blobs_[i]->ToProto(param->add_blobs(), write_diff); }}} // namespace caffe#endif // CAFFE_LAYER_H_
layer.cpp
#include <boost/thread.hpp>#include "caffe/layer.hpp"namespace caffe {/*下面是多线程操作函数的实现*/template <typename Dtype>void Layer<Dtype>::InitMutex() { forward_mutex_.reset(new boost::mutex());}template <typename Dtype>void Layer<Dtype>::Lock() { if (IsShared()) { forward_mutex_->lock(); }}template <typename Dtype>void Layer<Dtype>::Unlock() { if (IsShared()) { forward_mutex_->unlock(); }}INSTANTIATE_CLASS(Layer);} // namespace caffe
感谢::::
http://www.cnblogs.com/louyihang-loves-baiyan/p/5152653.html
http://blog.csdn.net/mounty_fsc/article/details/51092906
http://blog.csdn.net/u011104550/article/details/51249387
http://blog.163.com/yuyang_tech/blog/static/2160500832015713105052452/
0 0
- caffe源码 之 layer类
- [Caffe]源码解析之Layer
- caffe源码理解之layer
- caffe源码解析之layer
- caffe源码解析之Layer层(1)
- caffe源码解析之Layer层(1)
- caffe源码阅读之layer(1)
- caffe源码 layer分析
- caffe源码学习:layer
- caffe源码:Layer
- caffe源码追踪--layer
- caffe源码解析之添加新的Layer(maxout)
- CAFFE源码学习笔记之七-layer_factory以及layer基类
- caffe源码阅读之layer(2)——DataLayer层
- caffe源码阅读之layer(2)——Euclidean_loss_layer层
- Caffe导读之layer
- caffe研究之layer
- Caffe源码解读(三):Layer类的源码解读
- java使用freemarker模版导出分页word
- edittext编辑框圆角形状
- SpringBoot+Maven项目实战(4):集成Mybatis
- studio警告: 最后一个参数使用了不准确的变量类型的 varargs 方法的非 varargs 调用
- Python中数组的一些特殊用法-1
- caffe源码 之 layer类
- LeetCode 412. Fizz Buzz
- [OpenGL]创建一个窗口
- 【Android】解决Listview侧滑与上下滑动问题+侧滑通用布局 DragRelativeLayout
- Jmeter-JDBC Request的Query Type
- MFC六大核心机制之一:MFC程序的初始化
- (十四)ArcGIS API For Javascript之几何服务
- c++单利对象的释放
- mysql常用命令行