Blob类中syncedmen.hpp源码阅读：
位置：caffe/include/caffe/syncedmem.hpp
#ifndef CAFFE_SYNCEDMEM_HPP_
#define CAFFE_SYNCEDMEM_HPP_
#include <cstdlib>
#ifdef USE_MKL
#include "mkl.h"
#endif
#include "caffe/common.hpp"
namespace caffe {
// If CUDA is available and in GPU mode, host memory will be allocated pinned,
// using cudaMallocHost. It avoids dynamic pinning for transfers (DMA).
// The improvement in performance seems negligible in the single GPU case,
// but might be more significant for parallel training. Most importantly,
// it improved stability for large models on many GPUs.
inline void CaffeMallocHost(void** ptr, size_t size, bool* use_cuda) {
#ifndef CPU_ONLY
if (Caffe::mode() == Caffe::GPU) {
CUDA_CHECK(cudaMallocHost(ptr, size));
*use_cuda = true;
return;
}
#endif
#ifdef USE_MKL
*ptr = mkl_malloc(size ? size:1, 64);
#else
*ptr = malloc(size);
#endif
*use_cuda = false;
CHECK(*ptr) << "host allocation of size " << size << " failed";
}
inline void CaffeFreeHost(void* ptr, bool use_cuda) {
#ifndef CPU_ONLY
if (use_cuda) {
CUDA_CHECK(cudaFreeHost(ptr));
return;
}
#endif
#ifdef USE_MKL
mkl_free(ptr);
#else
free(ptr);
#endif
}
/**
* @brief Manages memory allocation and synchronization between the host (CPU)
* and device (GPU).
*
* TODO(dox): more thorough description.
*/
class SyncedMemory {
public:
SyncedMemory(); //构造函数
explicit SyncedMemory(size_t size); //显示构造函数
~SyncedMemory(); //Getters/Setters
const void* cpu_data(); //只读获取cpu_data
void set_cpu_data(void* data); //设置cpu_data
const void* gpu_data(); //只读获取gpu_data
void set_gpu_data(void* data); //设置gpu_data
void* mutable_cpu_data(); //读写获取cpu_data
void* mutable_gpu_data(); //读写获取gpu_data
enum SyncedHead { UNINITIALIZED, HEAD_AT_CPU, HEAD_AT_GPU, SYNCED }; //状态机变量，表示4种状态：未初始化、CPU有效数据、GPU有效数据、已同步
SyncedHead head() const { return head_; } //获取当前状态机变量值
size_t size() const { return size_; } //获取当前存储空间尺寸
#ifndef CPU_ONLY
void async_gpu_push(const cudaStream_t& stream);
#endif
private:
void check_device();
void to_cpu(); //数据同步至CPU
void to_gpu(); //数据同步至GPU
void* cpu_ptr_; //位于CPU的数据指针
void* gpu_ptr_; //位于GPU的数据指针
size_t size_; //存储空间大小
SyncedHead head_; //状态机变量
bool own_cpu_data_; //标志是否拥有CPU数据所有权（不然，从别的对象共享）
bool cpu_malloc_use_cuda_;
bool own_gpu_data_; //标志是否拥有GPU数据所有权
int device_; //设备号
DISABLE_COPY_AND_ASSIGN(SyncedMemory);
}; // class SyncedMemory
} // namespace caffe
#endif // CAFFE_SYNCEDMEM_HPP_
Blob类实现的源码，blob.cpp源码阅读：
位置：caffe/src/caffe/blob.cpp
#include <climits>
#include <vector>
#include "caffe/blob.hpp"
#include "caffe/common.hpp"
#include "caffe/syncedmem.hpp"
#include "caffe/util/math_functions.hpp"
namespace caffe {
template <typename Dtype>
void Blob<Dtype>::Reshape(const int num, const int channels, const int height,
const int width) {
vector<int> shape(4);
shape[0] = num;
shape[1] = channels;
shape[2] = height;
shape[3] = width;
Reshape(shape);
}
//变维函数，将（num, channels, height, weight) 参数转换为vector<int>,然后调用重载的变维函数void
template <typename Dtype>
void Blob<Dtype>::Reshape(const vector<int>& shape) {
CHECK_LE(shape.size(), kMaxBlobAxes); //保证vector<=kMaxBlobAxes
count_ = 1; //用于计算元素的总数=num*channels*height*width
shape_.resize(shape.size()); //变量维度重置
if (!shape_data_ || shape_data_->size() < shape.size() * sizeof(int)) {
shape_data_.reset(new SyncedMemory(shape.size() * sizeof(int)));
}
int* shape_data = static_cast<int*>(shape_data_->mutable_cpu_data());
for (int i = 0; i < shape.size(); ++i) {
CHECK_GE(shape[i], 0); //保证每维尺度都>=0
if (count_ != 0) {
CHECK_LE(shape[i], INT_MAX / count_) << "blob size exceeds INT_MAX";
} //保证count_不溢出
count_ *= shape[i]; //count_累乘
shape_[i] = shape[i]; //为变量赋值
shape_data[i] = shape[i];
}
if (count_ > capacity_) { //判断新的count_是否已超出当前分配空间容量
capacity_ = count_; //扩容，为data_和diff_重新分配空间
data_.reset(new SyncedMemory(capacity_ * sizeof(Dtype)));
diff_.reset(new SyncedMemory(capacity_ * sizeof(Dtype)));
}
}
template <typename Dtype>
void Blob<Dtype>::Reshape(const BlobShape& shape) {
CHECK_LE(shape.dim_size(), kMaxBlobAxes);
vector<int> shape_vec(shape.dim_size());
for (int i = 0; i < shape.dim_size(); ++i) {
shape_vec[i] = shape.dim(i);
}
Reshape(shape_vec);
}
template <typename Dtype>
void Blob<Dtype>::ReshapeLike(const Blob<Dtype>& other) {
Reshape(other.shape());
}
template <typename Dtype>
Blob<Dtype>::Blob(const int num, const int channels, const int height,
const int width)
// 调用reshape之前，必须初始化capacity_
: capacity_(0) {
Reshape(num, channels, height, width);
}
template <typename Dtype>
Blob<Dtype>::Blob(const vector<int>& shape)
// 调用reshape之前，必须初始化capacity_
: capacity_(0) {
Reshape(shape);
}
template <typename Dtype>
const int* Blob<Dtype>::gpu_shape() const { //只读取gpu data 指针
CHECK(shape_data_);
return (const int*)shape_data_->gpu_data();
}
template <typename Dtype>
const Dtype* Blob<Dtype>::cpu_data() const { //只读取cpu data 指针
CHECK(data_); //检查data_不为空
return (const Dtype*)data_->cpu_data();
}
template <typename Dtype>
void Blob<Dtype>::set_cpu_data(Dtype* data) { //修改cpu data 指针
CHECK(data);
// Make sure CPU and GPU sizes remain equal
size_t size = count_ * sizeof(Dtype);
if (data_->size() != size) {
data_.reset(new SyncedMemory(size));
diff_.reset(new SyncedMemory(size));
}
data_->set_cpu_data(data); //设置成员变量值为传入参数值
}
template <typename Dtype>
const Dtype* Blob<Dtype>::gpu_data() const {
CHECK(data_);
return (const Dtype*)data_->gpu_data();
}
template <typename Dtype>
void Blob<Dtype>::set_gpu_data(Dtype* data) { //修改gpu data 指针
CHECK(data);
// Make sure CPU and GPU sizes remain equal
size_t size = count_ * sizeof(Dtype);
if (data_->size() != size) {
data_.reset(new SyncedMemory(size));
diff_.reset(new SyncedMemory(size));
}
data_->set_gpu_data(data);
}
template <typename Dtype>
const Dtype* Blob<Dtype>::cpu_diff() const { //只读取cpu_diff指针
CHECK(diff_);
return (const Dtype*)diff_->cpu_data();
}
template <typename Dtype>
const Dtype* Blob<Dtype>::gpu_diff() const { //只读取gpu_diff指针
CHECK(diff_);
return (const Dtype*)diff_->gpu_data();
}
template <typename Dtype>
Dtype* Blob<Dtype>::mutable_cpu_data() { //读写访问cpu_data指针
CHECK(data_);
return static_cast<Dtype*>(data_->mutable_cpu_data());
}
template <typename Dtype>
Dtype* Blob<Dtype>::mutable_gpu_data() { //读写访问gpu_data指针
CHECK(data_);
return static_cast<Dtype*>(data_->mutable_gpu_data());
}
template <typename Dtype>
Dtype* Blob<Dtype>::mutable_cpu_diff() { //读写访问cpu_diff指针
CHECK(diff_);
return static_cast<Dtype*>(diff_->mutable_cpu_data());
}
template <typename Dtype>
Dtype* Blob<Dtype>::mutable_gpu_diff() { //读写访问gpu_diff指针
CHECK(diff_);
return static_cast<Dtype*>(diff_->mutable_gpu_data());
}
template <typename Dtype>
void Blob<Dtype>::ShareData(const Blob& other) { //共享另一个Blob的data指针
CHECK_EQ(count_, other.count());
data_ = other.data();
}
template <typename Dtype>
void Blob<Dtype>::ShareDiff(const Blob& other) { //共享另一个Blob的diff指针
CHECK_EQ(count_, other.count());
diff_ = other.diff();
}
// The "update" method is used for parameter blobs in a Net, which are stored
// as Blob<float> or Blob<double> -- hence we do not define it for
// Blob<int> or Blob<unsigned int>.
template <> void Blob<unsigned int>::Update() { NOT_IMPLEMENTED; }
template <> void Blob<int>::Update() { NOT_IMPLEMENTED; }
template <typename Dtype>
void Blob<Dtype>::Update() {
// We will perform update based on where the data is located.
switch (data_->head()) { //data在那，就在那更新
case SyncedMemory::HEAD_AT_CPU:
// data位于cpu
caffe_axpy<Dtype>(count_, Dtype(-1),
static_cast<const Dtype*>(diff_->cpu_data()),
static_cast<Dtype*>(data_->mutable_cpu_data()));
break;
case SyncedMemory::HEAD_AT_GPU: // data位于gpu,或者同步
case SyncedMemory::SYNCED:
#ifndef CPU_ONLY
// perform computation on GPU
caffe_gpu_axpy<Dtype>(count_, Dtype(-1),
static_cast<const Dtype*>(diff_->gpu_data()),
static_cast<Dtype*>(data_->mutable_gpu_data()));
#else
NO_GPU;
#endif
break;
default:
LOG(FATAL) << "Syncedmem not initialized.";
}
}
template <> unsigned int Blob<unsigned int>::asum_data() const { //计算data的L1范数
NOT_IMPLEMENTED;
return 0;
}
template <> int Blob<int>::asum_data() const {
NOT_IMPLEMENTED;
return 0;
}
template <typename Dtype>
Dtype Blob<Dtype>::asum_data() const {
if (!data_) { return 0; }
switch (data_->head()) {
case SyncedMemory::HEAD_AT_CPU:
return caffe_cpu_asum(count_, cpu_data()); //执行cpu上的asum计算
case SyncedMemory::HEAD_AT_GPU:
case SyncedMemory::SYNCED:
#ifndef CPU_ONLY
{
Dtype asum;
caffe_gpu_asum(count_, gpu_data(), &asum); ////执行gpu上的asum计算
return asum;
}
#else
NO_GPU;
#endif
case SyncedMemory::UNINITIALIZED:
return 0;
default:
LOG(FATAL) << "Unknown SyncedMemory head state: " << data_->head();
}
return 0;
}
template <> unsigned int Blob<unsigned int>::asum_diff() const { //计算diff的L1范数
NOT_IMPLEMENTED;
return 0;
}
template <> int Blob<int>::asum_diff() const {
NOT_IMPLEMENTED;
return 0;
}
template <typename Dtype>
Dtype Blob<Dtype>::asum_diff() const {
if (!diff_) { return 0; }
switch (diff_->head()) {
case SyncedMemory::HEAD_AT_CPU:
return caffe_cpu_asum(count_, cpu_diff());
case SyncedMemory::HEAD_AT_GPU:
case SyncedMemory::SYNCED:
#ifndef CPU_ONLY
{
Dtype asum;
caffe_gpu_asum(count_, gpu_diff(), &asum);
return asum;
}
#else
NO_GPU;
#endif
case SyncedMemory::UNINITIALIZED:
return 0;
default:
LOG(FATAL) << "Unknown SyncedMemory head state: " << diff_->head();
}
return 0;
}
template <> unsigned int Blob<unsigned int>::sumsq_data() const { ////执行data上的L2范数计算
NOT_IMPLEMENTED;
return 0;
}
template <> int Blob<int>::sumsq_data() const {
NOT_IMPLEMENTED;
return 0;
}
template <typename Dtype>
Dtype Blob<Dtype>::sumsq_data() const {
Dtype sumsq;
const Dtype* data;
if (!data_) { return 0; }
switch (data_->head()) {
case SyncedMemory::HEAD_AT_CPU:
data = cpu_data();
sumsq = caffe_cpu_dot(count_, data, data);
break;
case SyncedMemory::HEAD_AT_GPU:
case SyncedMemory::SYNCED:
#ifndef CPU_ONLY
data = gpu_data();
caffe_gpu_dot(count_, data, data, &sumsq);
#else
NO_GPU;
#endif
break;
case SyncedMemory::UNINITIALIZED:
return 0;
default:
LOG(FATAL) << "Unknown SyncedMemory head state: " << data_->head();
}
return sumsq;
}
template <> unsigned int Blob<unsigned int>::sumsq_diff() const { //计算diff的L2范数
NOT_IMPLEMENTED;
return 0;
}
template <> int Blob<int>::sumsq_diff() const {
NOT_IMPLEMENTED;
return 0;
}
template <typename Dtype>
Dtype Blob<Dtype>::sumsq_diff() const {
Dtype sumsq;
const Dtype* diff;
if (!diff_) { return 0; }
switch (diff_->head()) {
case SyncedMemory::HEAD_AT_CPU:
diff = cpu_diff();
sumsq = caffe_cpu_dot(count_, diff, diff);
break;
case SyncedMemory::HEAD_AT_GPU:
case SyncedMemory::SYNCED:
#ifndef CPU_ONLY
diff = gpu_diff();
caffe_gpu_dot(count_, diff, diff, &sumsq);
break;
#else
NO_GPU;
#endif
case SyncedMemory::UNINITIALIZED:
return 0;
default:
LOG(FATAL) << "Unknown SyncedMemory head state: " << data_->head();
}
return sumsq;
}
template <> void Blob<unsigned int>::scale_data(unsigned int scale_factor) { //对data进行幅度缩放
NOT_IMPLEMENTED;
}
template <> void Blob<int>::scale_data(int scale_factor) {
NOT_IMPLEMENTED;
}
template <typename Dtype>
void Blob<Dtype>::scale_data(Dtype scale_factor) {
Dtype* data;
if (!data_) { return; }
switch (data_->head()) {
case SyncedMemory::HEAD_AT_CPU:
data = mutable_cpu_data();
caffe_scal(count_, scale_factor, data); // data[i]=data[i]*scale_factor,i=0,1,2,...
return;
case SyncedMemory::HEAD_AT_GPU:
case SyncedMemory::SYNCED:
#ifndef CPU_ONLY
data = mutable_gpu_data();
caffe_gpu_scal(count_, scale_factor, data);
return;
#else
NO_GPU;
#endif
case SyncedMemory::UNINITIALIZED:
return;
default:
LOG(FATAL) << "Unknown SyncedMemory head state: " << data_->head();
}
}
template <> void Blob<unsigned int>::scale_diff(unsigned int scale_factor) {//对diff进行幅度缩放
NOT_IMPLEMENTED;
}
template <> void Blob<int>::scale_diff(int scale_factor) {
NOT_IMPLEMENTED;
}
template <typename Dtype>
void Blob<Dtype>::scale_diff(Dtype scale_factor) {
Dtype* diff;
if (!diff_) { return; }
switch (diff_->head()) {
case SyncedMemory::HEAD_AT_CPU:
diff = mutable_cpu_diff();
caffe_scal(count_, scale_factor, diff);
return;
case SyncedMemory::HEAD_AT_GPU:
case SyncedMemory::SYNCED:
#ifndef CPU_ONLY
diff = mutable_gpu_diff();
caffe_gpu_scal(count_, scale_factor, diff);
return;
#else
NO_GPU;
#endif
case SyncedMemory::UNINITIALIZED:
return;
default:
LOG(FATAL) << "Unknown SyncedMemory head state: " << diff_->head();
}
}
template <typename Dtype>
bool Blob<Dtype>::ShapeEquals(const BlobProto& other) { //判断形状是否相同
if (other.has_num() || other.has_channels() ||
other.has_height() || other.has_width()) { //转变旧维度信息为vector
// Using deprecated 4D Blob dimensions --
// shape is (num, channels, height, width).
// Note: we do not use the normal Blob::num(), Blob::channels(), etc.
// methods as these index from the beginning of the blob shape, where legacy
// parameter blobs were indexed from the end of the blob shape (e.g., bias
// Blob shape (1 x 1 x 1 x N), IP layer weight Blob shape (1 x 1 x M x N)).
return shape_.size() <= 4 &&
LegacyShape(-4) == other.num() &&
LegacyShape(-3) == other.channels() &&
LegacyShape(-2) == other.height() &&
LegacyShape(-1) == other.width();
}
vector<int> other_shape(other.shape().dim_size());
for (int i = 0; i < other.shape().dim_size(); ++i) {
other_shape[i] = other.shape().dim(i);
}
return shape_ == other_shape; //直接对比
}
template <typename Dtype> //从其他Blob对象拷贝data(可选diff),必要时变维
void Blob<Dtype>::CopyFrom(const Blob& source, bool copy_diff, bool reshape) {
if (source.count() != count_ || source.shape() != shape_) {
if (reshape) {
ReshapeLike(source); //变维
} else {
LOG(FATAL) << "Trying to copy blobs of different sizes.";
}
}
switch (Caffe::mode()) {
case Caffe::GPU:
if (copy_diff) {
caffe_copy(count_, source.gpu_diff(),
static_cast<Dtype*>(diff_->mutable_gpu_data()));
} else {
caffe_copy(count_, source.gpu_data(),
static_cast<Dtype*>(data_->mutable_gpu_data()));
}
break;
case Caffe::CPU:
if (copy_diff) {
caffe_copy(count_, source.cpu_diff(),
static_cast<Dtype*>(diff_->mutable_cpu_data()));
} else {
caffe_copy(count_, source.cpu_data(),
static_cast<Dtype*>(data_->mutable_cpu_data()));
}
break;
default:
LOG(FATAL) << "Unknown caffe mode.";
}
}
template <typename Dtype> //从BlobProto中加载一个Blob，适用于从磁盘载入之前导出的Blob
void Blob<Dtype>::FromProto(const BlobProto& proto, bool reshape) {
if (reshape) {
vector<int> shape;
if (proto.has_num() || proto.has_channels() ||
proto.has_height() || proto.has_width()) {
// Using deprecated 4D Blob dimensions --
// shape is (num, channels, height, width).
shape.resize(4);
shape[0] = proto.num();
shape[1] = proto.channels();
shape[2] = proto.height();
shape[3] = proto.width();
} else {
shape.resize(proto.shape().dim_size());
for (int i = 0; i < proto.shape().dim_size(); ++i) {
shape[i] = proto.shape().dim(i);
}
}
Reshape(shape); //Blob按照维度信息变维
} else {
CHECK(ShapeEquals(proto)) << "shape mismatch (reshape not set)";
}
// copy data
Dtype* data_vec = mutable_cpu_data();
if (proto.double_data_size() > 0) {
CHECK_EQ(count_, proto.double_data_size());
for (int i = 0; i < count_; ++i) {
data_vec[i] = proto.double_data(i); //加在double data
}
} else {
CHECK_EQ(count_, proto.data_size());
for (int i = 0; i < count_; ++i) {
data_vec[i] = proto.data(i); //不然加载float data
}
}
if (proto.double_diff_size() > 0) {
CHECK_EQ(count_, proto.double_diff_size());
Dtype* diff_vec = mutable_cpu_diff();
for (int i = 0; i < count_; ++i) {
diff_vec[i] = proto.double_diff(i);
}
} else if (proto.diff_size() > 0) {
CHECK_EQ(count_, proto.diff_size());
Dtype* diff_vec = mutable_cpu_diff();
for (int i = 0; i < count_; ++i) {
diff_vec[i] = proto.diff(i);
}
}
}
template <> //将Blob中的data(可选diff）导出到Blobproto结构体，便于存储到磁盘文件中
void Blob<double>::ToProto(BlobProto* proto, bool write_diff) const {
proto->clear_shape();
for (int i = 0; i < shape_.size(); ++i) {
proto->mutable_shape()->add_dim(shape_[i]); //重置proto的维度，保证和Blob相同
}
proto->clear_double_data(); //清除data
proto->clear_double_diff(); //清除diff
const double* data_vec = cpu_data();
for (int i = 0; i < count_; ++i) {
proto->add_double_data(data_vec[i]);
}
if (write_diff) { //如果有write_diff的需求
const double* diff_vec = cpu_diff();
for (int i = 0; i < count_; ++i) {
proto->add_double_diff(diff_vec[i]); //将diff导出到proto
}
}
}
template <>
void Blob<float>::ToProto(BlobProto* proto, bool write_diff) const {
proto->clear_shape();
for (int i = 0; i < shape_.size(); ++i) {
proto->mutable_shape()->add_dim(shape_[i]);
}
proto->clear_data();
proto->clear_diff();
const float* data_vec = cpu_data();
for (int i = 0; i < count_; ++i) {
proto->add_data(data_vec[i]);
}
if (write_diff) {
const float* diff_vec = cpu_diff();
for (int i = 0; i < count_; ++i) {
proto->add_diff(diff_vec[i]);
}
}
}
INSTANTIATE_CLASS(Blob); //实例化Blob类模板（float,double)
template class Blob<int>;
template class Blob<unsigned int>;
} // namespace caffe
Blob类实现的源码，Layer.hpp源码阅读：
#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: //显式构造函数，从LayerParameter对象加载对象
/**
* 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)
: layer_param_(param) {
// Set phase and copy blobs (if there are any).
phase_ = param.phase(); //设置当前阶段（trainning/test)
if (layer_param_.blobs_size() > 0) {
blobs_.resize(layer_param_.blobs_size()); //按layer_param_设置本身blob对象个数，
并依次将新Blob尺寸调整与layer_param_的一致。
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() {} //虚构函数
/**
* @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) { //配置函数，实现常用层配接口，不可被覆盖
CheckBlobCounts(bottom, top); //检查Blob
LayerSetUp(bottom, top); //与层类型相关的配置过程
Reshape(bottom, top); //对Blob变形
SetLossWeights(top); //设置损失权重因子Blob
}
/**
* @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) {} //层配置（虚）函数，做特定类型层相关配置，
由该类型自己实现
/**
* @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.
*/
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.
*/
inline Dtype Forward(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top); //前向传播
/**
* @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.
*/
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() { //共享参数
return blobs_;
}
/**
* @brief Returns the layer parameter.
*/
const LayerParameter& layer_param() const { return layer_param_; } //层参数
/**
* @brief Writes the layer parameter to a protocol buffer
*/
virtual void ToProto(LayerParameter* param, bool write_diff = false); //把层参数写入protocol
/**
* @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); //返回与给定索引处的顶部Blob相关联的标量损失
}
/**
* @brief Sets the loss associated with a top blob at a given index.
*/
inline void set_loss(const int top_index, const Dtype value) { //设置与输出相关的损失
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 ""; }
/**
* @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; } //返回确切的输入Blob数量，否则返回-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; } //返回最小的输入Blob数量，否则返回-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; } //返回最大的输入Blob数量，否则返回-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; } //返回确切的输出Blob数量，否则返回-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; } //如果图层需要相等数量的底部和底部，则返回true
/**
* @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 { //允许反向传播
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) { //参数反向传播
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) { //设置参数反向传播
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_; //层参数存于protobuf
/** The phase: TRAIN or TEST */
Phase phase_; //阶段：训练or测试
/** The vector that stores the learnable parameters as a set of blobs. */
vector<shared_ptr<Blob<Dtype> > > blobs_; //向量存储共享参数
/** Vector indicating whether to compute the diff of each param blob. */
vector<bool> param_propagate_down_; //指明是否需要计算参数偏差
/** The vector that indicates whether each top blob has a non-zero weight in
* the objective function. */
vector<Dtype> loss_; //指示每个顶部Blob是否具有非零权重的向量
/** @brief Using the CPU device, compute the layer output. */
virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) = 0; //CPU前向计算
/**
* @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, //CPU后向计算
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.
*/
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.
*/
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:
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> //前向传播
inline Dtype Layer<Dtype>::Forward(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
Dtype loss = 0;
Reshape(bottom, top);
switch (Caffe::mode()) {
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> //后向传播
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LayerParameter序列化为协议缓冲区
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_
Blob类实现的源码，include/caffe/net.hpp源码阅读：
Net相当于一张图纸描述文件为*.prototxt。Blob视作Caffe砖石，Layer比作Caffe的墙面，Net是设计Caffe的图纸。
#ifndef CAFFE_NET_HPP_
#define CAFFE_NET_HPP_
#include <map>
#include <set>
#include <string>
#include <utility>
#include <vector>
#include "caffe/blob.hpp"
#include "caffe/common.hpp"
#include "caffe/layer.hpp"
#include "caffe/proto/caffe.pb.h"
namespace caffe {
/**
* @brief Connects Layer%s together into a directed acyclic graph (DAG)有向无环图
* specified by a NetParameter.
*
* TODO(dox): more thorough description.
*/
template <typename Dtype>
class Net {
public:
explicit Net(const NetParameter& param); //显式构造函数
explicit Net(const string& param_file, Phase phase,
const int level = 0, const vector<string>* stages = NULL);
virtual ~Net() {} //虚构函数
/// @brief Initialize a network with a NetParameter.
void Init(const NetParameter& param); //用NetParameter初始化网络
/**
* @brief Run Forward and return the result.
*
*/
const vector<Blob<Dtype>*>& Forward(Dtype* loss = NULL); //运行前向传播，输入Blob已经预先填好
/// @brief DEPRECATED; use Forward() instead.
const vector<Blob<Dtype>*>& ForwardPrefilled(Dtype* loss = NULL) { //前向传播的几种形式
LOG_EVERY_N(WARNING, 1000) << "DEPRECATED: ForwardPrefilled() "
<< "will be removed in a future version. Use Forward().";
return Forward(loss);
}
/**
* The From and To variants of Forward and Backward operate on the
* (topological) ordering by which the net is specified. For general DAG
* networks, note that (1) computing from one layer to another might entail
* extra computation on unrelated branches, and (2) computation starting in
* the middle may be incorrect if all of the layers of a fan-in are not
* included.
*/
Dtype ForwardFromTo(int start, int end);
Dtype ForwardFrom(int start);
Dtype ForwardTo(int end);
/// @brief DEPRECATED; set input blobs then use Forward() instead.
const vector<Blob<Dtype>*>& Forward(const vector<Blob<Dtype>* > & bottom,
Dtype* loss = NULL); //制定序列化的输入BlobProtoVector进行前向传播，返回序列化输出
/**
* @brief Zeroes out the diffs of all net parameters.
* Should be run before Backward.
*/
void ClearParamDiffs(); //在反向传播之前，请零所有权值的diff域
/**
* The network backward should take no input and output, since it solely
* computes the gradient w.r.t the parameters, and the data has already been
* provided during the forward pass.
*/
void Backward(); //反向传播
void BackwardFromTo(int start, int end);
void BackwardFrom(int start);
void BackwardTo(int end);
/**
* @brief Reshape all layers from bottom to top.
*
* This is useful to propagate changes to layer sizes without running
* a forward pass, e.g. to compute output feature size.
*/
void Reshape(); //变形
Dtype ForwardBackward() { //前向传播+反向传播，输入Bottom Blob,输出loss
Dtype loss;
Forward(&loss);
Backward();
return loss;
}
/// @brief Updates the network weights based on the diff values computed.
void Update(); //根据已经计算好的diff更新权重
/**
* @brief Shares weight data of owner blobs with shared blobs.
*
* Note: this is called by Net::Init, and thus should normally not be
* called manually.
*/
void ShareWeights(); //权重共享
/**
* @brief For an already initialized net, implicitly copies (i.e., using no
* additional memory) the pre-trained layers from another Net.
*/
void ShareTrainedLayersWith(const Net* other); //从一个训练好的网络共享权重
// For an already initialized net, CopyTrainedLayersFrom() copies the already
// trained layers from another net parameter instance.
/**
* @brief For an already initialized net, copies the pre-trained layers from
* another Net.
*/
void CopyTrainedLayersFrom(const NetParameter& param);
void CopyTrainedLayersFrom(const string& trained_filename);
void CopyTrainedLayersFromBinaryProto(const string& trained_filename);
void CopyTrainedLayersFromHDF5(const string& trained_filename);
/// @brief Writes the net to a proto.
void ToProto(NetParameter* param, bool write_diff = false) const; //把net写入proto
/// @brief Writes the net to an HDF5 file.
void ToHDF5(const string& filename, bool write_diff = false) const; //把net写入HDF5
/// @brief returns the network name.
inline const string& name() const { return name_; } //返回网络名
/// @brief returns the layer names
inline const vector<string>& layer_names() const { return layer_names_; } //返回Layer名
/// @brief returns the blob names
inline const vector<string>& blob_names() const { return blob_names_; } //返回Blob名
/// @brief returns the blobs
inline const vector<shared_ptr<Blob<Dtype> > >& blobs() const { //返回blob_
return blobs_;
}
/// @brief returns the layers
inline const vector<shared_ptr<Layer<Dtype> > >& layers() const {
return layers_;
}
/// @brief returns the phase: TRAIN or TEST
inline Phase phase() const { return phase_; } //返回阶段， TRAIN or TEST
/**
* @brief returns the bottom vecs for each layer -- usually you won't
* need this unless you do per-layer checks such as gradients.
*/
inline const vector<vector<Blob<Dtype>*> >& bottom_vecs() const {
return bottom_vecs_;
}
/**
* @brief returns the top vecs for each layer -- usually you won't
* need this unless you do per-layer checks such as gradients.
*/
inline const vector<vector<Blob<Dtype>*> >& top_vecs() const { //返回顶部Blob
return top_vecs_;
}
/// @brief returns the ids of the top blobs of layer i
inline const vector<int> & top_ids(int i) const { 返回某层顶部Blob的id
CHECK_GE(i, 0) << "Invalid layer id";
CHECK_LT(i, top_id_vecs_.size()) << "Invalid layer id";
return top_id_vecs_[i];
}
/// @brief returns the ids of the bottom blobs of layer i
inline const vector<int> & bottom_ids(int i) const {
CHECK_GE(i, 0) << "Invalid layer id";
CHECK_LT(i, bottom_id_vecs_.size()) << "Invalid layer id";
return bottom_id_vecs_[i];
}
inline const vector<vector<bool> >& bottom_need_backward() const { //返回底部是否需要BP
return bottom_need_backward_;
}
inline const vector<Dtype>& blob_loss_weights() const { //返回每个Blob是否需要参与loss计算
return blob_loss_weights_;
}
inline const vector<bool>& layer_need_backward() const { //返回层是否需要参与loss计算
return layer_need_backward_;
}
/// @brief returns the parameters
inline const vector<shared_ptr<Blob<Dtype> > >& params() const { //返回参数
return params_;
}
inline const vector<Blob<Dtype>*>& learnable_params() const { //返回可学习参数
return learnable_params_;
}
/// @brief returns the learnable parameter learning rate multipliers
inline const vector<float>& params_lr() const { return params_lr_; } //返回可学习参数
inline const vector<bool>& has_params_lr() const { return has_params_lr_; } //bool,是否有可学习参数
/// @brief returns the learnable parameter decay multipliers
inline const vector<float>& params_weight_decay() const { //返回权重延迟率
return params_weight_decay_;
}
inline const vector<bool>& has_params_decay() const {
return has_params_decay_;
}
const map<string, int>& param_names_index() const { //每个参数名称与顺序索引关系
return param_names_index_;
}
inline const vector<int>& param_owners() const { return param_owners_; }
inline const vector<string>& param_display_names() const { //返回权重Blob名称
return param_display_names_;
}
/// @brief 输入和输出 blob 的数量
inline int num_inputs() const { return net_input_blobs_.size(); }
inline int num_outputs() const { return net_output_blobs_.size(); }
inline const vector<Blob<Dtype>*>& input_blobs() const { //网络输入Blob
return net_input_blobs_;
}
inline const vector<Blob<Dtype>*>& output_blobs() const { //网络输出Blob
return net_output_blobs_;
}
inline const vector<int>& input_blob_indices() const { //网络输入Blob名称与顺序索引关系
return net_input_blob_indices_;
}
inline const vector<int>& output_blob_indices() const {
return net_output_blob_indices_;
}
bool has_blob(const string& blob_name) const;
const shared_ptr<Blob<Dtype> > blob_by_name(const string& blob_name) const;
bool has_layer(const string& layer_name) const;
const shared_ptr<Layer<Dtype> > layer_by_name(const string& layer_name) const;
void set_debug_info(const bool value) { debug_info_ = value; } //设置BUG信息
// Helpers for Init.
/**
* @brief Remove layers that the user specified should be excluded given the current
* phase, level, and stage.
*/
static void FilterNet(const NetParameter& param, //删除用户指定的层，在当前情况下应排除这些层阶段，级别和阶段。
NetParameter* param_filtered);
/// @brief return whether NetState state meets NetStateRule rule
static bool StateMeetsRule(const NetState& state, const NetStateRule& rule,
const string& layer_name); //返回网络状态是否满足RELU
// Invoked at specific points during an iteration
class Callback { //在迭代过程中的特定点调用
protected:
virtual void run(int layer) = 0;
template <typename T>
friend class Net;
};
const vector<Callback*>& before_forward() const { return before_forward_; }
void add_before_forward(Callback* value) {
before_forward_.push_back(value);
}
const vector<Callback*>& after_forward() const { return after_forward_; }
void add_after_forward(Callback* value) {
after_forward_.push_back(value);
}
const vector<Callback*>& before_backward() const { return before_backward_; }
void add_before_backward(Callback* value) {
before_backward_.push_back(value);
}
const vector<Callback*>& after_backward() const { return after_backward_; }
void add_after_backward(Callback* value) {
after_backward_.push_back(value);
}
protected:
// Helpers for Init.
/// @brief Append a new top blob to the net. //新增一个top blob给网络
void AppendTop(const NetParameter& param, const int layer_id,
const int top_id, set<string>* available_blobs,
map<string, int>* blob_name_to_idx);
/// @brief Append a new bottom blob to the net. //新增一个bottom blob给网络
int AppendBottom(const NetParameter& param, const int layer_id,
const int bottom_id, set<string>* available_blobs,
map<string, int>* blob_name_to_idx);
/// @brief Append a new parameter blob to the net. //新增参数
void AppendParam(const NetParameter& param, const int layer_id,
const int param_id);
/// @brief Helper for displaying debug info in Forward.
void ForwardDebugInfo(const int layer_id); //显示前向传播BUG
/// @brief Helper for displaying debug info in Backward.
void BackwardDebugInfo(const int layer_id); //显示后向传播BUG
/// @brief Helper for displaying debug info in Update.
void UpdateDebugInfo(const int param_id); //更新BUG信息
/// @brief The network name
string name_; //网络名
/// @brief The phase: TRAIN or TEST
Phase phase_; //状态
/// @brief Individual layers in the net
vector<shared_ptr<Layer<Dtype> > > layers_;
vector<string> layer_names_;
map<string, int> layer_names_index_;
vector<bool> layer_need_backward_;
/// @brief the blobs storing intermediate results between the layer.
vector<shared_ptr<Blob<Dtype> > > blobs_; //在层之间存储中间结果的Blob
vector<string> blob_names_;
map<string, int> blob_names_index_;
vector<bool> blob_need_backward_;
/// bottom_vecs存储包含每一层输入的向量。
/// They don't actually host the blobs (blobs_ does), so we simply store
/// pointers.
vector<vector<Blob<Dtype>*> > bottom_vecs_;
vector<vector<int> > bottom_id_vecs_;
vector<vector<bool> > bottom_need_backward_;
/// top_vecs存储包含每一层输出的向量
vector<vector<Blob<Dtype>*> > top_vecs_;
vector<vector<int> > top_id_vecs_;
///每个Blob的损失（或目标）函数中的权重向量，以及目录
/// indexed by blob_id.
vector<Dtype> blob_loss_weights_;
vector<vector<int> > param_id_vecs_;
vector<int> param_owners_;
vector<string> param_display_names_;
vector<pair<int, int> > param_layer_indices_;
map<string, int> param_names_index_;
/// blob indices for the input and the output of the net 网络输入和输出的目录
vector<int> net_input_blob_indices_;
vector<int> net_output_blob_indices_;
vector<Blob<Dtype>*> net_input_blobs_;
vector<Blob<Dtype>*> net_output_blobs_;
/// The parameters in the network.
vector<shared_ptr<Blob<Dtype> > > params_; //网络参数
vector<Blob<Dtype>*> learnable_params_;
/**
* The mapping from params_ -> learnable_params_: we have
* learnable_param_ids_.size() == params_.size(),
* and learnable_params_[learnable_param_ids_[i]] == params_[i].get()
* if and only if params_[i] is an "owner"; otherwise, params_[i] is a sharer
* and learnable_params_[learnable_param_ids_[i]] gives its owner.
*/
vector<int> learnable_param_ids_; //可训练参数目录
/// the learning rate multipliers for learnable_params_
vector<float> params_lr_; //参数学习率
vector<bool> has_params_lr_; //是否有参数学习率
/// the weight decay multipliers for learnable_params_
vector<float> params_weight_decay_; //权重延迟率
vector<bool> has_params_decay_;
/// The bytes of memory used by this net
size_t memory_used_; //网络所需内存
/// Whether to compute and display debug info for the net.
bool debug_info_; //是否计算和显示网络的调试信息
// Callbacks
vector<Callback*> before_forward_;
vector<Callback*> after_forward_;
vector<Callback*> before_backward_;
vector<Callback*> after_backward_;
DISABLE_COPY_AND_ASSIGN(Net); //禁止拷贝构造函数、赋值运算函数
};
} // namespace caffe
#endif // CAFFE_NET_HPP_