Blob类是caffe中对处理和传递的实际数据的封装，是caffe中基本的数据存储单元，包括前向传播中的图像数据，反向传播中的梯度数据以及网络层间的中间数据变量（包括权值，偏置等），训练模型的参数等等，可以说在caffe中，无数据不blob。
blob可以认为是按C风格连续存储的N维数组，在硬件上可以认为是在内存中的一块连续的内存块。
补充一点智能指针的知识：
C++中的动态内存管理是通过new和delete运算符完成的，没有及时delete释放内存或者提前释放内存都可能造成内存异常，导致内存泄漏，或者是引用了非法的内存指针。
C++ 11 标准库提供了智能指针（smart pointer）来管理动态内存对象，这种智能指针的智能之处在于可以自动释放内存对象。智能指针分为两种，一种是shared_ptr，允许多了个指针同时指向同一个对象，另一种是unique_ptr，同时只能有一个指针指向内存对象。 智能指针是模板类而不是指针，创建一个智能指针时，必须指出智能指针的对象可以指向的类型。
blob.hpp文件注释：
#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类型的整形kMaxBlobAxes定义了Blob最大的维度，Blob的一般维度是4，图像数量*图像通道*图像宽度*图像高度
const int kMaxBlobAxes = 32;
namespace caffe { //Blob类也定义在caffe命名空间下
/**
* @brief A wrapper around SyncedMemory holders serving as the basic
* computational unit through which Layer%s, Net%s, and Solver%s
* interact.
*
* TODO(dox): more thorough description.
*/
template <typename Dtype> //类模板
class Blob {
public:
Blob() //无参构造函数
: data_(), diff_(), count_(0), capacity_(0) {}
//explicit关键字的作用是防止单参数构造函数的隐式转换， 对于含有多个未初始化值的构造函数无效
//shape是一个int型的向量，包含一个blob的维度，图像深度，高，宽信息
//这两个构造函数都会在内部调用Reshape函数，用来设置或者修改当前blob的shape_，count_和capacity_属性
/// @brief Deprecated; use <code>Blob(const vector<int>& shape)</code>.
explicit Blob(const int num, const int channels, const int height,
const int width);
explicit Blob(const vector<int>& shape);
/// @brief Deprecated; use <code>Reshape(const vector<int>& shape)</code>.
//Reshape函数的作用是创建或调整blob的shape_，count_和capacity_属性
void Reshape(const int num, const int channels, const int height,
const int width);
/*
* @brief Change the dimensions of the blob, allocating new memory if
* necessary.
*Reshape函数可以用来创建一个初始化的内存分配信息，也可以调整前向传播过程中网络层的数据输出尺度
* This function can be called both to create an initial allocation
* of memory, and to adjust the dimensions of a top blob during Layer::Reshape
blob的大小改变后，只有在已分配的内存不够的情况下才会重新分配内存， 并且新增的内存将不会被释放
* or Layer::Forward.When changing the size of blob, memory will only be
* reallocated if sufficient memory does not already exist, and excess memory
* will never be freed.
*需要注意的是直接改变输入blob的大小是错误的，它们应该在数据从低层向高层的传播中数据量增加的时候被调用
* Note that reshaping an input blob and immediately calling Net::Backward is
* an error; either Net::Forward or Net::Reshape need to be called to
* propagate the new input shape to higher layers.
*/
//通过类型为vector<int>类型的shape设置shape_，count_和capacity_ 的大小
void Reshape(const vector<int>& shape);
//通过类型为BlobShape类对象shape设置shape_，count_和capacity_ 的大小
//BlobShape是在caffe.pb.h中定义的类，含有维度信息，继承自protobuf::Message
void Reshape(const BlobShape& shape);
//通过其他的blob对象类设置bolb的shape_，count_和capacity_ 的大小
void ReshapeLike(const Blob& other);
//inline定义的是内联函数，作用是将代码直接复制到调用处，节省函数调用开销，代价是增加了代码量
//shape_string 函数用于获取bolb的打印信息(shape_和count_值)
inline string shape_string() const {
ostringstream stream;
for (int i = 0; i < shape_.size(); ++i) {
stream << shape_[i] << " ";
}
stream << "(" << count_ << ")";
return stream.str();
}
//获取当前blob的shape_信息
inline const vector<int>& shape() const { return shape_; }
/**
* @brief Returns the dimension of the index-th axis (or the negative index-th
* axis from the end, if index is negative).
*
* @param index the axis index, which may be negative as it will be
* "canonicalized" using CanonicalAxisIndex.
* Dies on out of range index.
*/
//获取当前指定blob指定索引的维度值
inline int shape(int index) const {
return shape_[CanonicalAxisIndex(index)];
}
//获取blob的维数
inline int num_axes() const { return shape_.size(); }
//获取blob的元素个数
inline int count() const { return count_; }
/**
* @brief Compute the volume of a slice; i.e., the product of dimensions
* among a range of axes.
*
* @param start_axis The first axis to include in the slice.
*
* @param end_axis The first axis to exclude from the slice.
*/
//根据指定的开始维度和结束维度计算blob元素的个数
inline int count(int start_axis, int end_axis) const {
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;
}
/**
* @brief Compute the volume of a slice spanning from a particular first
* axis to the final axis.
*
* @param start_axis The first axis to include in the slice.
*/
//根据指定的开始维度计算剩下的blob元素个数，内部是通过调用上边定义的count函数实现的
inline int count(int start_axis) const {
return count(start_axis, num_axes());
}
/**
* @brief Returns the 'canonical' version of a (usually) user-specified axis,
* allowing for negative indexing (e.g., -1 for the last axis).
*
* @param axis_index the axis index.
* If 0 <= index < num_axes(), return index.
* If -num_axes <= index <= -1, return (num_axes() - (-index)),
* e.g., the last axis index (num_axes() - 1) if index == -1,
* the second to last if index == -2, etc.
* Dies on out of range index.
*/
//CanonicalAxisIndex是用于对blob的axis_index进行转化，允许axis_index的值是负值，通过
//CanonicalAxisIndex函数内定义的规则，转换成正值
inline int CanonicalAxisIndex(int axis_index) const {
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;
}
//获取当前blob的维度，推荐直接使用shape(0)获取
/// @brief Deprecated legacy shape accessor num: use shape(0) instead.
inline int num() const { return LegacyShape(0); }
//获取当前blob的通道数（深度），推荐直接使用shape(1)获取
/// @brief Deprecated legacy shape accessor channels: use shape(1) instead.
inline int channels() const { return LegacyShape(1); }
//获取当前blob的图像高度信息，推荐直接使用shape(2)获取
/// @brief Deprecated legacy shape accessor height: use shape(2) instead.
inline int height() const { return LegacyShape(2); }
//获取当前blob的图像宽度信息，推荐直接使用shape(3)获取
/// @brief Deprecated legacy shape accessor width: use shape(3) instead.
inline int width() const { return LegacyShape(3); }
//获取某一维度index下的信息，index要求在[0,3]或[-4，-1]区间内，貌似是对shape函数的封装，只是增加了形参的判定
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);
}
//通过blob的维度n，通道（图像深度）c，图像高度h和图像宽度w计算偏移量，由该偏移量可以
//唯一定位到bolb内的一张图像上的一个像素上
inline int offset(const int n, const int c = 0, const int h = 0,
const int w = 0) const {
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;
}
//根据vector<int>类型的indices计算偏移量
inline int offset(const vector<int>& indices) const {
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
*/
//复制外部的blob数据到本blob，根据情况拷贝data_数据还是diff_数据，以及是否重新分配大小
void CopyFrom(const Blob<Dtype>& source, bool copy_diff = false,
bool reshape = false);
//根据给定的维度，深度，宽高位置信息获取前向传播数据的一个元素的值
inline Dtype data_at(const int n, const int c, const int h,
const int w) const {
return cpu_data()[offset(n, c, h, w)];
}
//根据给定的维度，深度，宽高位置信息获取反向传播梯度diff_的一个元素的值
inline Dtype diff_at(const int n, const int c, const int h,
const int w) const {
return cpu_diff()[offset(n, c, h, w)];
}
//获取前向传播数据data_的指针
inline Dtype data_at(const vector<int>& index) const {
return cpu_data()[offset(index)];
}
//获取反向传播梯度diff_的指针
inline Dtype diff_at(const vector<int>& index) const {
return cpu_diff()[offset(index)];
}
//获取前向传播数据对象
inline const shared_ptr<SyncedMemory>& data() const {
CHECK(data_);
return data_;
}
//获取反向传播梯度对象
inline const shared_ptr<SyncedMemory>& diff() const {
CHECK(diff_);
return diff_;
}
const Dtype* cpu_data() const; //定义的获取cpu数据指针函数
void set_cpu_data(Dtype* data); //设置cpu数据
const int* gpu_shape() const; //返回GPU shape_数据指针
const Dtype* gpu_data() const; //返回GPU 数据指针
const Dtype* cpu_diff() const; //返回CPU上反向传播的梯度数据指针
const Dtype* gpu_diff() const; //返回GPU上反向传播的梯度数据指针
Dtype* mutable_cpu_data(); //以下加上mutable代表可以修改获取到的数据
Dtype* mutable_gpu_data();
Dtype* mutable_cpu_diff();
Dtype* mutable_gpu_diff();
//梯度下降过程中训练参数更新
void Update();
//从BlobProto中导入数据到当前blob，完成数据解析（反序列化）
void FromProto(const BlobProto& proto, bool reshape = true);
//把blob数据导入BlobProto，完成数据序列化
void ToProto(BlobProto* proto, bool write_diff = false) const;
//计算data_的L1范式：向量中各个元素绝对值之和
/// @brief Compute the sum of absolute values (L1 norm) of the data.
Dtype asum_data() const;
//计算diff_的L1范式：向量中各个元素绝对值之和
/// @brief Compute the sum of absolute values (L1 norm) of the diff.
Dtype asum_diff() const;
//计算data_的L2范式：向量中各个元素的平方和
/// @brief Compute the sum of squares (L2 norm squared) of the data.
Dtype sumsq_data() const;
//计算diff_的L2范式：向量中各个元素的平方和
/// @brief Compute the sum of squares (L2 norm squared) of the diff.
Dtype sumsq_diff() const;
//将data_数据乘以一个系数scale_factor
/// @brief Scale the blob data by a constant factor.
void scale_data(Dtype scale_factor);
//将diff _数据乘以一个系数scale_factor
/// @brief Scale the blob diff by a constant factor.
void scale_diff(Dtype scale_factor);
/**
* @brief Set the data_ shared_ptr to point to the SyncedMemory holding the
* data_ of Blob other -- useful in Layer%s which simply perform a copy
* in their Forward pass.
*
* This deallocates the SyncedMemory holding this Blob's data_, as
* shared_ptr calls its destructor when reset with the "=" operator.
*/
//将外部一个Blob对象的数据指针指向当前的blob的数据data_，从而实现数据共享
void ShareData(const Blob& other);
/**
* @brief Set the diff_ shared_ptr to point to the SyncedMemory holding the
* diff_ of Blob other -- useful in Layer%s which simply perform a copy
* in their Forward pass.
*
* This deallocates the SyncedMemory holding this Blob's diff_, as
* shared_ptr calls its destructor when reset with the "=" operator.
*/
//将外部一个Blob对象的梯度指针指向当前的blob的数据diff_，从而实现数据共享
void ShareDiff(const Blob& other);
//判断当前blob的shape_和BlobProto中的shape_是否相同
bool ShapeEquals(const BlobProto& other);
protected:
//后缀加上_表示是Blob的成员变量
shared_ptr<SyncedMemory> data_; //前向传播数据
shared_ptr<SyncedMemory> diff_; //反向传播梯度（偏差）数据
shared_ptr<SyncedMemory> shape_data_; //blob的训练数据
vector<int> shape_; //blob的训练数据的组织维度
int count_; //blob中所有元素的个数，值为shape_中4个参数的乘积
int capacity_; //blob的容积量
//禁用Blob类的拷贝和赋值操作
DISABLE_COPY_AND_ASSIGN(Blob);
}; // class Blob
} // namespace caffe
#endif // CAFFE_BLOB_HPP_
