Caffe源码阅读笔记(1):Blob

blob是caffe基础的数据结构，是用来保存学习到的参数以及网络传输过程中产生数据的类，数据的交换和存储都依赖于blob。
blob具有CPU和GPU之间同步的能力,它是4维的数组(Num, Channels, Height, Width)。
设Blob数据维度为 number N x channel K x height H x width W，Blob是row-major保存的，因此在(n, k, h, w)位置的值物理位置为((n * K + k) * H + h) * W + w，其中Number/N是batch size。

行主序和列主序 Row Major and Column Major
向量写为[1x3]矩阵形式：V=|xyz| , 被称为行主序(Row Major)。
向量写为[3x1]矩阵形式:V=∣∣∣∣xyz∣∣∣∣ , 被称为列主序(Column Major)。

先来看看头文件caffe/include/caffe/blob.hpp
Caffe类中成员变量名都带有后缀“_”,这样就容易区分临时变量和类成员变量。

#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;namespace caffe {/** * @brief A wrapper around SyncedMemory holders serving as the basic *        computational unit through which Layer%s, Net%s, and Solver%s *        interact. *      封装了SyncedMemory类，作为基本的计算单元使用于Layer，Net，Solver等 * TODO(dox): more thorough description. */template <typename Dtype>class Blob { public:  //构造函数  Blob()       : data_(), diff_(), count_(0), capacity_(0) {}  /// @brief Deprecated; use <code>Blob(const vector<int>& shape)</code>.  //显式构造函数  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>.  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.   *        改变blob当前的尺寸，必要时从新分配内存   * 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   * 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.   *   * 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.   */  void Reshape(const vector<int>& shape);  void Reshape(const BlobShape& shape);  void ReshapeLike(const Blob& other);  //得到Blob形状字符串用于打印log  inline string shape_string() const {    ostringstream stream;    for (int i = 0; i < shape_.size(); ++i) {      stream << shape_[i] << " ";    }    stream << "(" << count_ << ")";    return stream.str();  }  //返回Blob形状  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.   */  //返回第index维度的尺寸  inline int shape(int index) const {    return shape_[CanonicalAxisIndex(index)];  }  //返回维度的数目  inline int num_axes() const { return shape_.size(); }  //返回Blob中元素的总数  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.   */  //返回从start_axis到end_axis的元素总数  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.   */  //返回从start_axis开始的元素总数  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.   */  //转换坐标轴索引，将[-N，N]转换为[0,N),负索引表示从后往前访问，-1表示最后一个元素，-2表示第N-2个元素，以此类推  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;  }  //获取某一维的尺寸,Blob是一个4维数组，维度从低到高分别为：num，channels，height，weight  /// @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); }  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);  }  //计算偏移量  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   */  //拷贝Blob  void CopyFrom(const Blob<Dtype>& source, bool copy_diff = false,      bool reshape = false);  //存取器（getter/setter）  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)];  }  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)];  }  inline const shared_ptr<SyncedMemory>& data() const {    CHECK(data_);    return data_;  }  inline const shared_ptr<SyncedMemory>& diff() const {    CHECK(diff_);    return diff_;  }  const Dtype* cpu_data() const;  void set_cpu_data(Dtype* data);  const int* gpu_shape() const;  const Dtype* gpu_data() const;  const Dtype* cpu_diff() const;  const Dtype* gpu_diff() const;  Dtype* mutable_cpu_data();  Dtype* mutable_gpu_data();  Dtype* mutable_cpu_diff();  Dtype* mutable_gpu_diff();  void Update();  //反序列化，从BlobProto中恢复一个Blob对象  void FromProto(const BlobProto& proto, bool reshape = true);  //序列化函数，将内存中Blob对象保存到BlobProto中  void ToProto(BlobProto* proto, bool write_diff = false) const;  /// @brief Compute the sum of absolute values (L1 norm) of the data.  //计算data的L1范数  Dtype asum_data() const;  /// @brief Compute the sum of absolute values (L1 norm) of the diff.  //计算diff的L1范数  Dtype asum_diff() const;  /// @brief Compute the sum of squares (L2 norm squared) of the data.  //计算data的L2范数  Dtype sumsq_data() const;  /// @brief Compute the sum of squares (L2 norm squared) of the diff.  //计算diff的L2范数  Dtype sumsq_diff() const;  /// @brief Scale the blob data by a constant factor.  //data乘以一个标量  void scale_data(Dtype scale_factor);  /// @brief Scale the blob diff by a constant factor.  //diff乘以一个标量  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.   */  //共享另一个Blob的data  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.   */  //共享另一个Blob的diff  void ShareDiff(const Blob& other);  bool ShapeEquals(const BlobProto& other); protected:  shared_ptr<SyncedMemory> data_;   //存放指向data的指针  shared_ptr<SyncedMemory> diff_;   //存放指向diff的指针  shared_ptr<SyncedMemory> shape_data_;   vector<int> shape_;   //形状信息  int count_;   //存放有效元素数目信息  int capacity_;    //存放Blob容器的容量信息  DISABLE_COPY_AND_ASSIGN(Blob); //禁用拷贝构造函数，赋值运算符重载};  // class Blob}  // namespace caffe#endif  // CAFFE_BLOB_HPP_

[参考]：
caffe官方文档
《二十一天实战caffe》
Caffe的三级结构(Blobs,Layers,Nets)
caffe 中 BLOB的实现