caffe源码追踪--blob

#ifndef CAFFE_BLOB_HPP_
#define CAFFE_BLOB_HPP_
#include <algorithm>
#include <string>
#include <vector>
#include "caffe/common.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/syncedmem.hpp"
const int kMaxBlobAxes = 32;//blob最大维度数目为32
namespace caffe {
template <typename Dtype>//定义Blob的模板类
class Blob {
public:Blob(): data_(), diff_(), count_(0), capacity_(0) {}//默认构造函数
explicit Blob(const int num, const int channels, const int height,const int width);//不建议使用,用下面这个代替
explicit Blob(const vector<int>& shape);//explicit抑制了"可以用 单个形参来调用 的构造函数定义了从 形参类型 到 该类类型 的一个隐式转换"这种隐式转换。
void Reshape(const int num, const int channels, const int height,const int width);//不建议使用,用下面这个代替
void Reshape(const vector<int>& shape);//重塑blob维度,如果不够则开辟内存,多的内存不会被释放
void Reshape(const BlobShape& shape);
void ReshapeLike(const Blob& other);
inline string shape_string() const {//该函数用来将维度信息转化为字符串,比如1 3 1 1 (3)
ostringstream stream;
for (int i = 0; i < shape_.size(); ++i) {
stream << shape_[i] << " ";
}
stream << "(" << count_ << ")";
return stream.str();
}
inline const vector<int>& shape() const { return shape_; }//shape_存储维度信息的容器
inline int shape(int index) const {//获取index维度的维度数目
return shape_[CanonicalAxisIndex(index)];
}
inline int num_axes() const { return shape_.size(); }//获取总的维度数目,如图像通常4维
inline int count() const { return count_; }//获取总的blob数目(存储在count_里)
inline int count(int start_axis, int end_axis) const {//获取start_axis到end_axis的blob数目(包括start_axis,不包括end_axis)
CHECK_LE(start_axis, end_axis);
CHECK_GE(start_axis, 0);
CHECK_GE(end_axis, 0);
CHECK_LE(start_axis, num_axes());
CHECK_LE(end_axis, num_axes());
int count = 1;
for (int i = start_axis; i < end_axis; ++i) {
count *= shape(i);
}
return count;
}
inline int count(int start_axis) const {//获取start_axis到最后的blob总数目
return count(start_axis, num_axes());
}
inline int CanonicalAxisIndex(int axis_index) const {//获取维度索引号,eg:如果0<=index<=num_axes(),则返回index;若-num_axes <= index <= -1, 则返回num_axes() - (-index),比如最后一维是-1,倒数第二维是-2
CHECK_GE(axis_index, -num_axes())
<< "axis " << axis_index << " out of range for " << num_axes()
<< "-D Blob with shape " << shape_string();
CHECK_LT(axis_index, num_axes())
<< "axis " << axis_index << " out of range for " << num_axes()
<< "-D Blob with shape " << shape_string();
if (axis_index < 0) {
return axis_index + num_axes();
}
return axis_index;
}
inline int num() const { return LegacyShape(0); }//获取批处理大小,不建议使用,用shape(0)代替
inline int channels() const { return LegacyShape(1); }//获取通道数,不建议使用,用shape(1)代替
inline int height() const { return LegacyShape(2); }//获取高,不建议使用,用shape(2)代替
inline int width() const { return LegacyShape(3); }//获取宽,不建议使用,用shape(3)代替
inline int LegacyShape(int index) const {
CHECK_LE(num_axes(), 4)
<< "Cannot use legacy accessors on Blobs with > 4 axes.";
CHECK_LT(index, 4);
CHECK_GE(index, -4);
if (index >= num_axes() || index < -num_axes()) {
// Axis is out of range, but still in [0, 3] (or [-4, -1] for reverse
// indexing) -- this special case simulates the one-padding used to fill
// extraneous axes of legacy blobs.
return 1;
}
return shape(index);
}

inline int offset(const int n, const int c = 0, const int h = 0,
const int w = 0) const {//获取坐标(n,c,h,w)的物理位置 ((n * C + c) * H + h) * W + w
CHECK_GE(n, 0);
CHECK_LE(n, num());
CHECK_GE(channels(), 0);
CHECK_LE(c, channels());
CHECK_GE(height(), 0);
CHECK_LE(h, height());
CHECK_GE(width(), 0);
CHECK_LE(w, width());
return ((n * channels() + c) * height() + h) * width() + w;
}

inline int offset(const vector<int>& indices) const {//同上,接受的输入为索引向量
CHECK_LE(indices.size(), num_axes());
int offset = 0;
for (int i = 0; i < num_axes(); ++i) {
offset *= shape(i);
if (indices.size() > i) {
CHECK_GE(indices[i], 0);
CHECK_LT(indices[i], shape(i));
offset += indices[i];
}
}
return offset;
}
/**
* @brief Copy from a source Blob.
*
* @param source the Blob to copy from
* @param copy_diff if false, copy the data; if true, copy the diff
* @param reshape if false, require this Blob to be pre-shaped to the shape
*        of other (and die otherwise); if true, Reshape this Blob to other's
*        shape if necessary
*/
void CopyFrom(const Blob<Dtype>& source, bool copy_diff = false,
bool reshape = false);//拷贝数据,如果copy_diff为false,则拷贝数据,否则拷贝梯度;reshape如果为false,拷贝之前需要提前reshape,为true,则可以copy中进行reshape
inline Dtype data_at(const int n, const int c, const int h,
const int w) const {//实现at功能,即获取坐标(n,c,h,w)的数据
return cpu_data()[offset(n, c, h, w)];
}
inline Dtype diff_at(const int n, const int c, const int h,
const int w) const {//获取坐标(n,c,h,w)的梯度
return cpu_diff()[offset(n, c, h, w)];
}
inline Dtype data_at(const vector<int>& index) const {//同上
return cpu_data()[offset(index)];
}
inline Dtype diff_at(const vector<int>& index) const {//同上
return cpu_diff()[offset(index)];
}
inline const shared_ptr<SyncedMemory>& data() const {//获取数据的地址
CHECK(data_);
return data_;
}
inline const shared_ptr<SyncedMemory>& diff() const {//获取梯度的地址
CHECK(diff_);
return diff_;
}
const Dtype* cpu_data() const;//只读的CPU数据指针
void set_cpu_data(Dtype* data);//设置CPU数据
const int* gpu_shape() const;//只读GPU数据维度指针
const Dtype* gpu_data() const;//只读的GPU数据指针
const Dtype* cpu_diff() const;//只读CPU梯度指针
const Dtype* gpu_diff() const;//只读的GPU梯度指针
Dtype* mutable_cpu_data();//可写的CPU数据指针
Dtype* mutable_gpu_data();//可写的GPU数据指针
Dtype* mutable_cpu_diff();//可写的CPU梯度指针
Dtype* mutable_gpu_diff();//可写的GPU梯度指针
void Update();
void FromProto(const BlobProto& proto, bool reshape = true);//从proto中恢复一个blob对象
void ToProto(BlobProto* proto, bool write_diff = false) const;//将blob序列化为proto
Dtype asum_data() const;//计算数据的绝对值和
Dtype asum_diff() const;//计算梯度的绝对值和
Dtype sumsq_data() const;//计算数据的平方和
Dtype sumsq_diff() const;//计算梯度的平方和
void scale_data(Dtype scale_factor);//计算scale*data
void scale_diff(Dtype scale_factor);//计算scale*diff
void ShareData(const Blob& other);//共享数据,将other中指向data的指针赋给this指向data的指针，同时this之前指向的data会被释放。
void ShareDiff(const Blob& other);//共享梯度,将other中指向diff的指针赋给this指向diff的指针，同时this之前指向的diff会被释放。
bool ShapeEquals(const BlobProto& other);//判断形状是否相同
protected:
shared_ptr<SyncedMemory> data_;
shared_ptr<SyncedMemory> diff_;
shared_ptr<SyncedMemory> shape_data_;
vector<int> shape_;
int count_;
int capacity_;

DISABLE_COPY_AND_ASSIGN(Blob);
};  // class Blob

}  // namespace caffe

#endif  // CAFFE_BLOB_HPP_

#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);
}
template <typename Dtype>
void Blob<Dtype>::Reshape(const vector<int>& shape) {//shape_data_是指向SyncedMemory的智能指针
CHECK_LE(shape.size(), kMaxBlobAxes);
count_ = 1;
shape_.resize(shape.size());//shape_塑形
if (!shape_data_ || shape_data_->size() < shape.size() * sizeof(int)) {//如果shape_data_没有分配内存或是原有内存不够,重新分配
shape_data_.reset(new SyncedMemory(shape.size() * sizeof(int)));
}
int* shape_data = static_cast<int*>(shape_data_->mutable_cpu_data());//类型转换
for (int i = 0; i < shape.size(); ++i) {
CHECK_GE(shape[i], 0);
if (count_ != 0) {
CHECK_LE(shape[i], INT_MAX / count_) << "blob size exceeds INT_MAX";
}
count_ *= shape[i];//得到count_,即blob总数
shape_[i] = shape[i];//shape_赋值
shape_data[i] = shape[i];//shape_data赋值
}
if (count_ > capacity_) {//capacity_为数据块的容量,当不够时,才重新分配
capacity_ = count_;
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): capacity_(0) {//给blob申请空间
Reshape(num, channels, height, width);
}

template <typename Dtype>
Blob<Dtype>::Blob(const vector<int>& shape) : capacity_(0) {//给blob申请空间
Reshape(shape);
}
template <typename Dtype>
const int* Blob<Dtype>::gpu_shape() const {//获取指向gpu数据维度信息的指针
CHECK(shape_data_);
return (const int*)shape_data_->gpu_data();
}
template <typename Dtype>
const Dtype* Blob<Dtype>::cpu_data() const {//获取指向cpu数据的指针
CHECK(data_);
return (const Dtype*)data_->cpu_data();
}
template <typename Dtype>
void Blob<Dtype>::set_cpu_data(Dtype* data) {//将data_指向data指向的数据释放掉原数据,具体实现见SyncedMemory文件
CHECK(data);
data_->set_cpu_data(data);
}
template <typename Dtype>
const Dtype* Blob<Dtype>::gpu_data() const {//获取指向gpu只读数据的指针
CHECK(data_);
return (const Dtype*)data_->gpu_data();
}
template <typename Dtype>
const Dtype* Blob<Dtype>::cpu_diff() const {//获取指向cpu只读梯度的指针
CHECK(diff_);
return (const Dtype*)diff_->cpu_data();
}
template <typename Dtype>
const Dtype* Blob<Dtype>::gpu_diff() const {//获取指向gpu只读梯度的指针
CHECK(diff_);
return (const Dtype*)diff_->gpu_data();
}
template <typename Dtype>
Dtype* Blob<Dtype>::mutable_cpu_data() {//获取指向cpu可写数据的指针
CHECK(data_);
return static_cast<Dtype*>(data_->mutable_cpu_data());
}
template <typename Dtype>
Dtype* Blob<Dtype>::mutable_gpu_data() {//获取指向gpu可写数据的指针
CHECK(data_);
return static_cast<Dtype*>(data_->mutable_gpu_data());
}
template <typename Dtype>
Dtype* Blob<Dtype>::mutable_cpu_diff() {//获取指向cpu梯度的指针
CHECK(diff_);
return static_cast<Dtype*>(diff_->mutable_cpu_data());
}
template <typename Dtype>
Dtype* Blob<Dtype>::mutable_gpu_diff() {//获取指向gpu梯度的指针
CHECK(diff_);
return static_cast<Dtype*>(diff_->mutable_gpu_data());
}
template <typename Dtype>
void Blob<Dtype>::ShareData(const Blob& other) {//将data_指向other中的数据
CHECK_EQ(count_, other.count());
data_ = other.data();
}
template <typename Dtype>
void Blob<Dtype>::ShareDiff(const Blob& other) {//将diff_指向other中的梯度
CHECK_EQ(count_, other.count());
diff_ = other.diff();
}
template <> void Blob<unsigned int>::Update() { NOT_IMPLEMENTED; }//函数模板显示具体化
template <> void Blob<int>::Update() { NOT_IMPLEMENTED; }//同上
template <> void Blob<bool>::Update() { NOT_IMPLEMENTED; }//同上
template <typename Dtype>
void Blob<Dtype>::Update() {
switch (data_->head()) {
case SyncedMemory::HEAD_AT_CPU://在CPU上计算
caffe_axpy<Dtype>(count_, Dtype(-1),
static_cast<const Dtype*>(diff_->cpu_data()),
static_cast<Dtype*>(data_->mutable_cpu_data()));//Y=Y-X,(X,Y)
break;
case SyncedMemory::HEAD_AT_GPU:
case SyncedMemory::SYNCED:
#ifndef CPU_ONLY//在GPU上计算
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 {
NOT_IMPLEMENTED;
return 0;
}
template <> int Blob<int>::asum_data() const {
NOT_IMPLEMENTED;
return 0;
}
template <> bool Blob<bool>::asum_data() const {
NOT_IMPLEMENTED;
return 0;
}
template <typename Dtype>
Dtype Blob<Dtype>::asum_data() const {//数据的L1范数
if (!data_) { return 0; }
switch (data_->head()) {
case SyncedMemory::HEAD_AT_CPU:
return caffe_cpu_asum(count_, cpu_data());
case SyncedMemory::HEAD_AT_GPU:
case SyncedMemory::SYNCED:
#ifndef CPU_ONLY
{
Dtype asum;
caffe_gpu_asum(count_, gpu_data(), &asum);
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 {
NOT_IMPLEMENTED;
return 0;
}
template <> int Blob<int>::asum_diff() const {
NOT_IMPLEMENTED;
return 0;
}
template <> bool Blob<bool>::asum_diff() const {
NOT_IMPLEMENTED;
return 0;
}
template <typename Dtype>
Dtype Blob<Dtype>::asum_diff() const {//梯度的L1范数
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 {
NOT_IMPLEMENTED;
return 0;
}

template <> int Blob<int>::sumsq_data() const {
NOT_IMPLEMENTED;
return 0;
}
template <> bool Blob<bool>::sumsq_data() const {
NOT_IMPLEMENTED;
return 0;
}
template <typename Dtype>
Dtype Blob<Dtype>::sumsq_data() const {//数据的L2范数
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 {
NOT_IMPLEMENTED;
return 0;
}
template <> int Blob<int>::sumsq_diff() const {
NOT_IMPLEMENTED;
return 0;
}
template <> bool Blob<bool>::sumsq_diff() const {
NOT_IMPLEMENTED;
return 0;
}
template <typename Dtype>
Dtype Blob<Dtype>::sumsq_diff() const {//梯度的L2范数
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) {
NOT_IMPLEMENTED;
}
template <> void Blob<int>::scale_data(int scale_factor) {
NOT_IMPLEMENTED;
}
template <> void Blob<bool>::scale_data(bool scale_factor) {
NOT_IMPLEMENTED;
}
template <typename Dtype>
void Blob<Dtype>::scale_data(Dtype scale_factor) {//Y=scale_factor*Y
Dtype* data;
if (!data_) { return; }
switch (data_->head()) {
case SyncedMemory::HEAD_AT_CPU:
data = mutable_cpu_data();
caffe_scal(count_, scale_factor, data);
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) {
NOT_IMPLEMENTED;
}
template <> void Blob<int>::scale_diff(int scale_factor) {
NOT_IMPLEMENTED;
}
template <> void Blob<bool>::scale_diff(bool scale_factor) {
NOT_IMPLEMENTED;
}
template <typename Dtype>
void Blob<Dtype>::scale_diff(Dtype scale_factor) {//Y_DIFF=scale_factor*Y_DIFF
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) {//BLOB形状是否一样
if (other.has_num() || other.has_channels() ||
other.has_height() || other.has_width()) {
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;
}
template <typename Dtype>
void Blob<Dtype>::CopyFrom(const Blob& source, bool copy_diff, bool reshape) {//若两个blob形状不一样,则看是否reshape,若可以,则reshape,否则报错;copy_diff控制拷贝数据还是梯度,若为真则是梯度,否则是数据
if (source.count() != count_ || source.shape() != shape_) {
if (reshape) {
ReshapeLike(source);
} 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>
void Blob<Dtype>::FromProto(const BlobProto& proto, bool reshape) {//从protocol buffer中读数据
if (reshape) {
vector<int> shape;
if (proto.has_num() || proto.has_channels() ||
proto.has_height() || proto.has_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);
} else {
CHECK(ShapeEquals(proto)) << "shape mismatch (reshape not set)";
}
//开始拷贝
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);
}
} else {
CHECK_EQ(count_, proto.data_size());
for (int i = 0; i < count_; ++i) {
data_vec[i] = proto.data(i);
}
}
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 <>
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]);
}
proto->clear_double_data();
proto->clear_double_diff();
const double* data_vec = cpu_data();
for (int i = 0; i < count_; ++i) {
proto->add_double_data(data_vec[i]);
}
if (write_diff) {
const double* diff_vec = cpu_diff();
for (int i = 0; i < count_; ++i) {
proto->add_double_diff(diff_vec[i]);
}
}
}

template <>
void Blob<float>::ToProto(BlobProto* proto, bool write_diff) const {//同上
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);
template class Blob<bool>;//实例化blob类
template class Blob<int>;
template class Blob<unsigned int>;

}  // namespace caffe