#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/device_alternate.hpp" //定义使用GPU还是CPU
//layer是基本类。
//深度网络:一层一层的layer,相互之间通过blob传输数据连接。
//layer必须要实现一个forward function,前递函数功能可以自己定义。
//在forward中,会从Input也就是layer的bottom(前一层)中获取blob,计算输出的blob
//实现一个反向传播,根据他们的Input的blob以及outPut的error gradient梯度误差计算得到该层的梯度误差
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.
*/
//Layer中三个重要参数:
//1.layer_param_:是protobuf文件中存储的layer参数
//2.blobs_:存储layer的参数,在程序中用的,layer学习到的参数
//3.param_propagate_down_:这个bool表示是否计算各个blob参数的diff,即传播误差。
explicit Layer(const LayerParameter& param)
: layer_param_(param) {
// Set phase and copy blobs (if there are any).
phase_ = param.phase(); //获得当前网络的phase,是train还是test,
if (layer_param_.blobs_size() > 0) {
blobs_.resize(layer_param_.blobs_size());
//在初始化列表初始化LayerParameter,之后blobs_这里存放的是一个指向blob类的shared_ptr指针的一个vector,这里是申请空间,然后将出传入的layer_param中的blob拷贝过来
for (int i = 0; i < layer_param_.blobs_size(); ++i) {
blobs_[i].reset(new Blob<Dtype>());
blobs_[i]->FromProto(layer_param_.blobs(i));
}
}
}
virtual ~Layer() {} //尝试从protobuf读取参数
/**
* @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.
*/
//根据实际的参数设置进行实现,对各种类型的参数初始化;
void SetUp(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
CheckBlobCounts(bottom, top); //1.check这个bottom和top的blob是否正确
LayerSetUp(bottom, top); //2.调用Layersetup对每一具体的层做进一步设置
Reshape(bottom, top); //3.再做reshape来设置top blobs和internal buffer.
SetLossWeights(top); //4.最后,设置loss weight multiplier的blob对每个非零的loss和weight,一般这个方法被继承后不会被重写
}
/**
* @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.
*/
virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {}
//LayerSetup就是对具体某一个layer的setup,被上面的那个函数所调用,ShareInParallel和IsShared和SetShared分别是用来返回并行状态和获取这一Layer是否被多个nets所共享。
//默认:除了data layer都是关闭的。在多个GPU下的Train阶段以及share是true的情况下,is_shared将会被置成true
/**
* @brief Adjust the shapes of top blobs and internal buffers to accomodate
* 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
* accomodate the bottom blobs.
*/
virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) = 0;
//这个reshape主要是layer用来根据输入的blob调节Internal buffer 以及输出的Blob
/**
* @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.
*/
//接下来是:重要函数
inline Dtype Forward(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top);
//Forward:是一个装饰器,继承之后再调用的调用其相应的forward_cpu或者forward_gpu,
//根据输入的Input data blob计算相应的output data blob,同时,会反应这一层Layer的total loss
/**
* @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 Forward_cpu and (optionally) Forward_gpu.
*/
inline void Backward(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down,
const vector<Blob<Dtype>*>& bottom);
//Backward:实现的是反向传播,也就是给定top blob的error gradient计算得到bottom的error gradient.
//输入时output blobs,在output blobs里面的diff存储的就是其相应的error gradients.
//其中propagate_down这个参数跟Bottom的长度是一样的,每一个index用来指定是否需要反向传播error gradients 到对应的bottom blob。
//bottom里面的diff区域存放的是Backward计算出来相应的gradient error
/**
* @brief Returns the vector of learnable parameter blobs.
*/
vector<shared_ptr<Blob<Dtype> > >& blobs() { //返回blobs
return blobs_;
}
/**
* @brief Returns the layer parameter.
*/
const LayerParameter& layer_param() const { return layer_param_; } //返回layer的参数parameter
/**
* @brief Writes the layer parameter to a protocol buffer
*/
virtual void ToProto(LayerParameter* param, bool write_diff = false); //将层参数写到protobuffer里
/**
* @brief Returns the scalar loss associated with a top blob at a given index.
*/
inline Dtype loss(const int top_index) const {
return (loss_.size() > top_index) ? loss_[top_index] : Dtype(0); //给定index返回相应的scalar loss
}
/**
* @brief Sets the loss associated with a top blob at a given index.
*/
inline void set_loss(const int top_index, const Dtype value) { //给定Index设置Loss
if (loss_.size() <= top_index) {
loss_.resize(top_index + 1, Dtype(0));
}
loss_[top_index] = value;
}
/**
* @brief Returns the layer type.
*/
virtual inline const char* type() const { return ""; } //返回layer的type
/**
* @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.
*/
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.
*/
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.
*/
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.
*/
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.
*/
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.
*/
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.
*/
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().
*/
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).
*/
virtual inline bool AllowForceBackward(const int bottom_index) const {
//用来设置是否强制梯度返回,因为有些层不需要梯度信息,后面两个函数分别查看以及设置是否需要计算梯度
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.
*/
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.
*/
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_;
/** The phase: TRAIN or TEST */
Phase phase_;
/** The vector that stores the learnable parameters as a set of blobs. */
vector<shared_ptr<Blob<Dtype> > > blobs_;
/** Vector indicating whether to compute the diff of each param blob. */
vector<bool> param_propagate_down_;
/** The vector that indicates whether each top blob has a non-zero weight in
* the objective function. */
vector<Dtype> loss_;
//分别计算cpu和gpu模式下的正向和反向传播
/** @brief Using the CPU device, compute the layer output. */
virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) = 0;
/**
* @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);
}
/**
* @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;
/**
* @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);
}
/**
* 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.
*/
//这个函数被setup调用,主要是check bottom和top 的blob是否match,这里面用了上面提到的ExactBottomBlobs()d等函数
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.
*/
//SetLoss是非常重要的一个步骤,是被Setup调用来初始化top bottom的weights,并且存储非零的Loss weights在diff blob里面
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);
}
}
}
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) {
Dtype loss = 0;
switch (Caffe::mode()) { //caffe::model:具体选择使用CPU或者GPU操作
case Caffe::CPU:
Forward_cpu(bottom, top);
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);
}
break;
case Caffe::GPU:
Forward_gpu(bottom, top);
#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);
loss += blob_loss;
}
#endif
break;
default:
LOG(FATAL) << "Unknown caffe mode.";
}
return loss;
}
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
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_
#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/device_alternate.hpp" //定义使用GPU还是CPU
//layer是基本类。
//深度网络:一层一层的layer,相互之间通过blob传输数据连接。
//layer必须要实现一个forward function,前递函数功能可以自己定义。
//在forward中,会从Input也就是layer的bottom(前一层)中获取blob,计算输出的blob
//实现一个反向传播,根据他们的Input的blob以及outPut的error gradient梯度误差计算得到该层的梯度误差
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.
*/
//Layer中三个重要参数:
//1.layer_param_:是protobuf文件中存储的layer参数
//2.blobs_:存储layer的参数,在程序中用的,layer学习到的参数
//3.param_propagate_down_:这个bool表示是否计算各个blob参数的diff,即传播误差。
explicit Layer(const LayerParameter& param)
: layer_param_(param) {
// Set phase and copy blobs (if there are any).
phase_ = param.phase(); //获得当前网络的phase,是train还是test,
if (layer_param_.blobs_size() > 0) {
blobs_.resize(layer_param_.blobs_size());
//在初始化列表初始化LayerParameter,之后blobs_这里存放的是一个指向blob类的shared_ptr指针的一个vector,这里是申请空间,然后将出传入的layer_param中的blob拷贝过来
for (int i = 0; i < layer_param_.blobs_size(); ++i) {
blobs_[i].reset(new Blob<Dtype>());
blobs_[i]->FromProto(layer_param_.blobs(i));
}
}
}
virtual ~Layer() {} //尝试从protobuf读取参数
/**
* @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.
*/
//根据实际的参数设置进行实现,对各种类型的参数初始化;
void SetUp(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
CheckBlobCounts(bottom, top); //1.check这个bottom和top的blob是否正确
LayerSetUp(bottom, top); //2.调用Layersetup对每一具体的层做进一步设置
Reshape(bottom, top); //3.再做reshape来设置top blobs和internal buffer.
SetLossWeights(top); //4.最后,设置loss weight multiplier的blob对每个非零的loss和weight,一般这个方法被继承后不会被重写
}
/**
* @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.
*/
virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {}
//LayerSetup就是对具体某一个layer的setup,被上面的那个函数所调用,ShareInParallel和IsShared和SetShared分别是用来返回并行状态和获取这一Layer是否被多个nets所共享。
//默认:除了data layer都是关闭的。在多个GPU下的Train阶段以及share是true的情况下,is_shared将会被置成true
/**
* @brief Adjust the shapes of top blobs and internal buffers to accomodate
* 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
* accomodate the bottom blobs.
*/
virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) = 0;
//这个reshape主要是layer用来根据输入的blob调节Internal buffer 以及输出的Blob
/**
* @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.
*/
//接下来是:重要函数
inline Dtype Forward(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top);
//Forward:是一个装饰器,继承之后再调用的调用其相应的forward_cpu或者forward_gpu,
//根据输入的Input data blob计算相应的output data blob,同时,会反应这一层Layer的total loss
/**
* @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 Forward_cpu and (optionally) Forward_gpu.
*/
inline void Backward(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down,
const vector<Blob<Dtype>*>& bottom);
//Backward:实现的是反向传播,也就是给定top blob的error gradient计算得到bottom的error gradient.
//输入时output blobs,在output blobs里面的diff存储的就是其相应的error gradients.
//其中propagate_down这个参数跟Bottom的长度是一样的,每一个index用来指定是否需要反向传播error gradients 到对应的bottom blob。
//bottom里面的diff区域存放的是Backward计算出来相应的gradient error
/**
* @brief Returns the vector of learnable parameter blobs.
*/
vector<shared_ptr<Blob<Dtype> > >& blobs() { //返回blobs
return blobs_;
}
/**
* @brief Returns the layer parameter.
*/
const LayerParameter& layer_param() const { return layer_param_; } //返回layer的参数parameter
/**
* @brief Writes the layer parameter to a protocol buffer
*/
virtual void ToProto(LayerParameter* param, bool write_diff = false); //将层参数写到protobuffer里
/**
* @brief Returns the scalar loss associated with a top blob at a given index.
*/
inline Dtype loss(const int top_index) const {
return (loss_.size() > top_index) ? loss_[top_index] : Dtype(0); //给定index返回相应的scalar loss
}
/**
* @brief Sets the loss associated with a top blob at a given index.
*/
inline void set_loss(const int top_index, const Dtype value) { //给定Index设置Loss
if (loss_.size() <= top_index) {
loss_.resize(top_index + 1, Dtype(0));
}
loss_[top_index] = value;
}
/**
* @brief Returns the layer type.
*/
virtual inline const char* type() const { return ""; } //返回layer的type
/**
* @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.
*/
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.
*/
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.
*/
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.
*/
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.
*/
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.
*/
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.
*/
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().
*/
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).
*/
virtual inline bool AllowForceBackward(const int bottom_index) const {
//用来设置是否强制梯度返回,因为有些层不需要梯度信息,后面两个函数分别查看以及设置是否需要计算梯度
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.
*/
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.
*/
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_;
/** The phase: TRAIN or TEST */
Phase phase_;
/** The vector that stores the learnable parameters as a set of blobs. */
vector<shared_ptr<Blob<Dtype> > > blobs_;
/** Vector indicating whether to compute the diff of each param blob. */
vector<bool> param_propagate_down_;
/** The vector that indicates whether each top blob has a non-zero weight in
* the objective function. */
vector<Dtype> loss_;
//分别计算cpu和gpu模式下的正向和反向传播
/** @brief Using the CPU device, compute the layer output. */
virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) = 0;
/**
* @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);
}
/**
* @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;
/**
* @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);
}
/**
* 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.
*/
//这个函数被setup调用,主要是check bottom和top 的blob是否match,这里面用了上面提到的ExactBottomBlobs()d等函数
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.
*/
//SetLoss是非常重要的一个步骤,是被Setup调用来初始化top bottom的weights,并且存储非零的Loss weights在diff blob里面
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);
}
}
}
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) {
Dtype loss = 0;
switch (Caffe::mode()) { //caffe::model:具体选择使用CPU或者GPU操作
case Caffe::CPU:
Forward_cpu(bottom, top);
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);
}
break;
case Caffe::GPU:
Forward_gpu(bottom, top);
#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);
loss += blob_loss;
}
#endif
break;
default:
LOG(FATAL) << "Unknown caffe mode.";
}
return loss;
}
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
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_