贯穿整个caffe的就是数据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"
#include "caffe/util/math_functions.hpp"

const int kMaxBlobAxes = INT_MAX;//blob最大维数目

namespace caffe {

/**
 * @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>
class Blob {
 public:
  Blob()//默认构造函数
       : data_(), diff_(), count_(0), capacity_(0) {}

  /// @brief Deprecated; use <code>Blob(const vector<int>& shape)</code>.
  //explicitkeyword的作用是禁止单參数构造函数的隐式转换
  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函数将num,channels,height,width传递给vector shape_ 
*/
  void Reshape(const int num, const int channels, const int height,
      const int width);
 /**
 *Blob作为一个最基础的类，当中构造函数开辟一个内存空间来存储数据。Reshape函数在Layer中的
 *reshape或者forward 操作中来adjust the dimensions of a top blob。同一时候在改变Blob大小时，
 *内存将会被又一次分配假设内存大小不够了，而且额外的内存将不会被释放。
对input的blob进行reshape,
 *假设立刻调用Net::Backward是会出错的，由于reshape之后，要么Net::forward或者Net::Reshape就会
 *被调用来将新的input shape 传播到高层
 */
  //依据shape来初始化shape_和shape_data_，以及为data_ 和diff_ 分配空间。
 
  void Reshape(const vector<int>& shape);
  void Reshape(const BlobShape& shape);
  void ReshapeLike(const Blob& other);
  //iniline主要是将代码进行复制，扩充，会使代码总量上升，优点就是能够节省调用的开销,以string形式获取shape_。用于打印blob的log
  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shape_
  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index维的大小，返回某一维的尺寸
  inline int shape(int index) const {
    return shape_[CanonicalAxisIndex(index)];
  }
//获取维的个数
  inline int num_axes() const { return shape_.size(); }
//获取当前data的大小
  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.
   */
/*多个count()函数，主要还是为了统计Blob的容量（volume）。或者是某一片（slice），
从某个axis到详细某个axis的shape乘积。
*/
//获取某几维数据的大小
  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.
   */
//获取某一维到结束数据的大小
  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 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.
   */
  //Blob的Index是能够从负坐标開始读的,标准化索引。主要是对參数索引进行标准化，以满足要求，转换坐标轴索引[-N。N]为[0，N]
  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;
  }
  //Blob中的4个基本变量num,channel,height,width能够直接通过shape(0),shape(1),shape(2),shape(3)来訪问
  /// @brief Deprecated legacy shape accessor num: use shape(0) instead.
  inline int num() const { return LegacyShape(0); }
  /// @brief Deprecated legacy shape accessor channels: use shape(1) instead.
  inline int channels() const { return LegacyShape(1); }
  /// @brief Deprecated legacy shape accessor height: use shape(2) instead.
  inline int height() const { return LegacyShape(2); }
  /// @brief Deprecated legacy shape accessor width: use shape(3) instead.
  inline int width() const { return LegacyShape(3); }
//data_维数不大于4时才干使用。功能同shape()相似。
  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);
  }
  //计算offset,offset计算的方式也支持两种方式。一种直接指定n,c,h,w或者放到一个vector中进行计算。
  //偏移量是依据相应的n,c,h,w，返回的offset是((n*channels()+c)*height()+h)*width()+w
  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;
  }

  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
   */
  //按值拷贝blob到当前blob。一个blob中copy数据 ，通过开关控制是否copy_diff,假设是False则copy data。reshape控制是否须要reshape
  void CopyFrom(const Blob<Dtype>& source, bool copy_diff = false,
      bool reshape = false);
/*这一部分函数主要通过给定的位置訪问数据，依据位置计算与数据起始
  的偏差offset，在通过cpu_data*指针获得地址
*/
//获取某位置的data_数据
  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)];
  }
//获取某位置的diff_数据
  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)];
  }

  inline Dtype data_at(const vector<int>& index) const {
    return cpu_data()[offset(index)];
  }

  inline Dtype diff_at(const vector<int>& index) const {
    return cpu_diff()[offset(index)];
  }
//获取data_
  inline const shared_ptr<SyncedMemory>& data() const {
    CHECK(data_);
    return data_;
  }
//获取diff_
  inline const shared_ptr<SyncedMemory>& diff() const {
    CHECK(diff_);
    return diff_;
  }
  //这里有data和diff两类数据，而这个diff就是我们所熟知的偏差。前者主要存储
  //前向传递的数据，而后者存储的是反向传播中的梯度
  const Dtype* cpu_data() const;//仅仅读获取data_ cpu指针
  void set_cpu_data(Dtype* data);//设置data_的cpu指针，仅仅是改动了指针
  const Dtype* gpu_data() const;//获取data_的gpu指针
  const Dtype* cpu_diff() const;//获取diff_的cpu指针
  const Dtype* gpu_diff() const;//获取diff_的gpu指针
  Dtype* mutable_cpu_data();//见SyncedMemory的mutable_cpu_data()，mutable是可读写訪问
  Dtype* mutable_gpu_data();//见SyncedMemory的mutable_gpu_data();
  Dtype* mutable_cpu_diff();//见SyncedMemory的mutable_cpu_data();
  Dtype* mutable_gpu_diff();//见SyncedMemory的mutable_gpu_data();
  //更新data_的数据,减去diff_的数据，就是合并data和diff
  void Update();
/*
当中用到math_functions.hpp中的函数caffe_axpy(),该函数封装了cblas_saxpy。实现的是Y=alpha*X+Y。

由此，知该函数的功能是data_=(data_-diff_)。另外。该函数仅仅实现了对double和float型数据，
对于unsigned int和int由于该函数主要是在Net中被调用。仅仅有Blob<float>和Blob<double>型式，
因此未定义unsigned int和int。
从proto中恢复一个blob对象
*/
  void FromProto(const BlobProto& proto, bool reshape = true);
/*
由BlobProto对Blob进行赋值操作。reshape代表是否同意改动shape_的大小。
须要注意的是再这里有double和float两种类型的数据 ，将blob序列化为proto。在代码中能够看到详细的体现
*/
  void ToProto(BlobProto* proto, bool write_diff = false) const;

  /// @brief Compute the sum of absolute values (L1 norm) of the data.
/*
功能：计算L1范数
说明：当中用到了math_function.hpp中的函数caffe_cpu_asum()和caffe_gpu_asum，实现的功能是对向量X求其每一个元素绝对值的和，不同的是X分别在cpu和gpu中。
*/
  Dtype asum_data() const;
  /// @brief Compute the sum of absolute values (L1 norm) of the diff.
  Dtype asum_diff() const;
  /// @brief Compute the sum of squares (L2 norm squared) of the data.
/*
功能：计算L2范数。
说明：用到了math_function.hpp中的caffe_cpu_dot(),caffe_cpu_strided_dot(),caffe_gpu_dot(), caffe_gpu_strided_dot()。
详细就是就向量X的平方和。

*/
  Dtype sumsq_data() const;
  /// @brief Compute the sum of squares (L2 norm squared) of the diff.
  Dtype sumsq_diff() const;

  /// @brief Scale the blob data by a constant factor.
/*
功能：正规化data_。
说明：用到math_function.hpp中的caffe_scal()和caffe_gpu_scal()函数，就是对向量X乘上一个因子。
*/
  void scale_data(Dtype 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.
   */
  void ShareData(const Blob& other);//本Blob共享other的data_
  /**
   * @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.
   */
  void ShareDiff(const Blob& other);//本Blob共享other的diff_

  bool ShapeEquals(const BlobProto& other);//推断other与本Blob形状是否同样。

 protected:
//data_指针。指针类型是shared_ptr。属于boost库的一个智能指针，这一部分主要用来申请内存存储data。data主要是正向传播的时候用的
  shared_ptr<SyncedMemory> data_;
//diff_主要用来存储偏差。update data
  shared_ptr<SyncedMemory> diff_;
//shape_存储Blob的形状
  vector<int> shape_;
//count_表示Blob中的元素个数，也就是个数*通道数*高度*宽度
  int count_;
//capacity表示当前的元素个数。由于Blob可能会reshape
  int capacity_;

  DISABLE_COPY_AND_ASSIGN(Blob);//禁止拷贝和赋值运算
};  // 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>
//该函数将num,channels,height,width传递给vector shape_ 
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) {
  CHECK_LE(shape.size(), kMaxBlobAxes);
  count_ = 1;
  shape_.resize(shape.size());//又一次定义vector shape_ 的size
  for (int i = 0; i < shape.size(); ++i) {
    CHECK_GE(shape[i], 0);//确保shape 每一个元素为正数
    CHECK_LE(shape[i], INT_MAX / count_) << "blob size exceeds INT_MAX";
    count_ *= shape[i];
    shape_[i] = shape[i];
  }
  //因为count_超过了当前capacity_ 因此须要又一次分配内存空间
  if (count_ > capacity_) {
    capacity_ = count_;
    data_.reset(new SyncedMemory(capacity_ * sizeof(Dtype)));
    diff_.reset(new SyncedMemory(capacity_ * sizeof(Dtype)));
  }
}

template <typename Dtype>// BlobShape 在caffe.proto 中定义
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);//dim 包括num。channels。height， width
  }
  Reshape(shape_vec);//用protobuf传递来dim 对shape_ 进行reshape
}
//用已知的Blob的shape来对shape_ 进行reshape
template <typename Dtype>
void Blob<Dtype>::ReshapeLike(const Blob<Dtype>& other) {
  Reshape(other.shape());
}
//用num。channels，height。 width 初始化
template <typename Dtype>
Blob<Dtype>::Blob(const int num, const int channels, const int height,
    const int width)
  // capacity_ must be initialized before calling Reshape
  : capacity_(0) {
  Reshape(num, channels, height, width);
}
//用shape 初始化
template <typename Dtype>
Blob<Dtype>::Blob(const vector<int>& shape)
  // capacity_ must be initialized before calling Reshape
  : capacity_(0) {
  Reshape(shape);
}
//返回cpu 中的数据
template <typename Dtype>
const Dtype* Blob<Dtype>::cpu_data() const {
  CHECK(data_);
  return (const Dtype*)data_->cpu_data();
}
// 清空cpu 数据
template <typename Dtype>
void Blob<Dtype>::set_cpu_data(Dtype* data) {
  CHECK(data);
  data_->set_cpu_data(data);
}
//返回gpu 中的数据
template <typename Dtype>
const Dtype* Blob<Dtype>::gpu_data() const {
  CHECK(data_);
  return (const Dtype*)data_->gpu_data();
}
//反向传播导数diff_ 操作函数,返回cpu 中的数据
template <typename Dtype>
const Dtype* Blob<Dtype>::cpu_diff() const {
  CHECK(diff_);
  return (const Dtype*)diff_->cpu_data();
}
//返回gpu 中的数据
template <typename Dtype>
const Dtype* Blob<Dtype>::gpu_diff() const {
  CHECK(diff_);
  return (const Dtype*)diff_->gpu_data();
}

template <typename Dtype>
Dtype* Blob<Dtype>::mutable_cpu_data() {
  CHECK(data_);
  return static_cast<Dtype*>(data_->mutable_cpu_data());
}

template <typename Dtype>
Dtype* Blob<Dtype>::mutable_gpu_data() {
  CHECK(data_);
  return static_cast<Dtype*>(data_->mutable_gpu_data());
}

template <typename Dtype>
Dtype* Blob<Dtype>::mutable_cpu_diff() {
  CHECK(diff_);
  return static_cast<Dtype*>(diff_->mutable_cpu_data());
}

template <typename Dtype>
Dtype* Blob<Dtype>::mutable_gpu_diff() {
  CHECK(diff_);
  return static_cast<Dtype*>(diff_->mutable_gpu_data());
}
//当前的blob 的data_ 指向已知blob的数据
template <typename Dtype>
void Blob<Dtype>::ShareData(const Blob& other) {
  CHECK_EQ(count_, other.count());
  data_ = other.data();
}
//当前的blob 的diff_ 指向已知blob的反向传播导数
template <typename Dtype>
void Blob<Dtype>::ShareDiff(const Blob& other) {
  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; }
//Updata函数用于參数blob的更新（weight，bias 等减去相应的导数）
template <typename Dtype>
void Blob<Dtype>::Update() {
  // We will perform update based on where the data is located.
  switch (data_->head()) {
  case SyncedMemory::HEAD_AT_CPU://数据在cpu上，则在cpu上进行计算
    // perform computation on 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:
  case SyncedMemory::SYNCED:
#ifndef CPU_ONLY//假设未定义CPU_ONLY。且数据在gpu上，则在gpu上进行计算
    // 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 {
  NOT_IMPLEMENTED;
  return 0;
}

template <> int Blob<int>::asum_data() const {
  NOT_IMPLEMENTED;
  return 0;
}
//返回data_ 中全部 element 的绝对值之和
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());
  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;
}
//返回diff_ 中全部 element 的绝对值之和
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 {
  NOT_IMPLEMENTED;
  return 0;
}

template <> int Blob<int>::sumsq_data() const {
  NOT_IMPLEMENTED;
  return 0;
}
//返回 data_ 中全部 element 的平方和
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 = http://www.mamicode.com/cpu_data();>