【Caffe代码解析】Blob
主要功能:
Blob 是Caffe作为传输数据的媒介,不管是网络权重參数,还是输入数据,都是转化为Blob数据结构来存储,网络,求解器等都是直接与此结构打交道的。
其直观的能够把它看成一个有4纬的结构体(包括数据和梯度)。而实际上,它们仅仅是一维的指针而已,其4维结构通过shape属性得以计算出来(依据C语言的数据顺序)。
其成员变量有:
protected:
shared_ptr<SyncedMemory> data_;// 存放数据
shared_ptr<SyncedMemory> diff_;//存放梯度
vector<int> shape_; //存放形状
int count_; //数据个数
int capacity_; //数据容量
成员函数,见的最多的有:
const Dtype* cpu_data() const; //cpu使用的数据
void set_cpu_data(Dtype* data);//用数据块的值来blob里面的data。
const Dtype* gpu_data() const;//返回不可更改的指针。下同
const Dtype* cpu_diff() const;
const Dtype* gpu_diff() const;
Dtype* mutable_cpu_data();//返回可更改的指针,下同
Dtype* mutable_gpu_data();
Dtype* mutable_cpu_diff();
Dtype* mutable_gpu_diff();
总之,带mutable_开头的意味着能够对返回的指针内容进行更改,而不带mutable_开头的返回const 指针。不能对其指针的内容进行改动,
int offset(const int n, const int c = 0, const int h = 0,const int w = 0) const
// 通过n,c,h,w 4个參数来计算一维向量的偏移量。
Dtype data_at(const int n, const int c, const int h,const int w) const//通过n,c,h,w 4个參数来来获取该向量位置上的值。
Dtype diff_at(const int n, const int c, const int h,const int w) const//同上
inline const shared_ptr<SyncedMemory>& data() const {
CHECK(data_);
return data_;//返回数据,不能改动
}
inline const shared_ptr<SyncedMemory>& diff() const {
CHECK(diff_);
return diff_;//返回梯度。不能改动
}
Reshape(...)//reshape 有多种多态的实现,能够是四个数字。长度为四的vector。其他blob等。
if (count_ > capacity_) {
capacity_ = count_;
data_.reset(new SyncedMemory(capacity_ * sizeof(Dtype)));
diff_.reset(new SyncedMemory(capacity_ * sizeof(Dtype)));
}//当空间不够的时候,须要扩大容量,reset。
源码:
#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;
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()
: data_(), diff_(), count_(0), capacity_(0) {}
/// @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>.
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.
*
* 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);
inline string shape_string() const {
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_; }
/**
* @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.
*/
inline int shape(int index) const {
return shape_[CanonicalAxisIndex(index)];
}
inline int num_axes() const { return shape_.size(); }
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.
*/
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.
*/
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.
*/
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;
}
/// @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);
}
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
*/
void CopyFrom(const Blob<Dtype>& source, bool copy_diff = false,
bool reshape = false);
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 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();
void FromProto(const BlobProto& proto, bool reshape = true);
void ToProto(BlobProto* proto, bool write_diff = false) const;
/// @brief Compute the sum of absolute values (L1 norm) of the data.
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.
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.
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);
/**
* @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);
bool ShapeEquals(const BlobProto& other);
protected:
shared_ptr<SyncedMemory> data_;
shared_ptr<SyncedMemory> diff_;
vector<int> shape_;
int count_;
int capacity_;
DISABLE_COPY_AND_ASSIGN(Blob);
}; // class Blob
} // namespace caffe
#endif // CAFFE_BLOB_HPP_
【Caffe代码解析】Blob的更多相关文章
- 【Caffe代码解析】compute_image_mean
功能: 计算训练数据库的平均图像. 由于平均归一化训练图像会对结果有提升,所以Caffe里面,提供了一个可选项. 用法: compute_image_mean [FLAGS] INPUT_DB [OU ...
- 【Caffe代码解析】Layer网络层
Layer 功能: 是全部的网络层的基类,当中.定义了一些通用的接口,比方前馈.反馈.reshape,setup等. #ifndef CAFFE_LAYER_H_ #define CAFFE_LAYE ...
- 【caffe Blob】caffe中与Blob相关的代码注释、使用举例
首先,Blob使用的小例子(通过运行结果即可知道相关功能): #include <vector> #include <caffe/blob.hpp> #include < ...
- 解析数学表达式 代码解析AST语法树
2019年2月20日09:18:22 AST语法树自己写代码解析的话就比较麻烦,有现成的库可以解析PHP,就像webpack就是自己解析js的语法代码,编译成各种版本的可用代码 github http ...
- (Caffe)基本类Blob,Layer,Net(一)
本文地址:http://blog.csdn.net/mounty_fsc/article/details/51085654 Caffe中,Blob.Layer,Net,Solver是最为核心的类,下面 ...
- matrix_multiply代码解析
matrix_multiply代码解析 关于matrix_multiply 程序执行代码里两个矩阵的乘法,并将相乘结果打印在屏幕上. 示例的主要目的是展现怎么实现一个自定义CPU计算任务. 参考:ht ...
- VBA常用代码解析
031 删除工作表中的空行 如果需要删除工作表中所有的空行,可以使用下面的代码. Sub DelBlankRow() DimrRow As Long DimLRow As Long Dimi As L ...
- [nRF51822] 12、基础实验代码解析大全 · 实验19 - PWM
一.PWM概述: PWM(Pulse Width Modulation):脉冲宽度调制技术,通过对一系列脉冲的宽度进行调制,来等效地获得所需要波形. PWM 的几个基本概念: 1) 占空比:占空比是指 ...
- [nRF51822] 11、基础实验代码解析大全 · 实验16 - 内部FLASH读写
一.实验内容: 通过串口发送单个字符到NRF51822,NRF51822 接收到字符后将其写入到FLASH 的最后一页,之后将其读出并通过串口打印出数据. 二.nRF51822芯片内部flash知识 ...
随机推荐
- HDU 1024 Max Sum Plus Plus(基础dp)
Max Sum Plus Plus Time Limit: 2000/1000 MS (Java/Others) Memory Limit: 65536/32768 K (Java/Others ...
- docker网络及Dockerfile
1.制作镜像 使用阿里的yum源,网址:https://opsx.alibaba.com/mirror,或者mirrors.aliyun.com,点击帮助,就会有弹框出来. docker pull c ...
- HDU 1496 Equations(哈希表)
[题目链接] http://acm.hdu.edu.cn/showproblem.php?pid=1496 [题目大意] 给出一个方程ax1^2+bx2^2+cx3^2+dx4^2=0,求-100到1 ...
- 【数学】【HAOI2008】【BZOJ1045糖果传递】【BZOJ3293分金币】论数学的重要性
BZOJ1045和BZOJ3293一模一样两道题,在这里我用1045来讲. 1045: [HAOI2008] 糖果传递 Time Limit: 10 Sec Memory Limit: 162 MB ...
- elasticsearch5.3.0 安装
公司有项目打算用elasticsearch,所以研究了下,目前最新版本5.3.0 安装 1.下载包 https://artifacts.elastic.co/downloads/elasticsea ...
- C语言基础之运算符优先级
1.运算符的优先级表 运算符的优先级(从高到低) 优先级 描述 运算符 1 括号 ().[] 2 正负号 +.- 3 自增自减,非 ++.--.! 4 乘除,取余 *./.% 5 加减 +.- 6 移 ...
- android RelativeLayout控件或view实现叠加效果
在开发android程序的时候,我们经常会遇到让控件或是view实现叠加的效果,一般这种情况,很多人会使用Framelayout来处理,可是有一个问题Framelayout布局在布局上会有很多限制,不 ...
- iOS教程:如何使用NSFetchedResultsController
不知不觉我们已经来到了Core Data系列教程的最后一部分了,在这里我们要讨论如何使用NSFetchedResultsController来优化我们的应用,提高应用的运行速度,减少其内存占用. 你是 ...
- 【Hadoop】Hadoop MR 自定义序列化类
1.基本概念 2.Mapper代码 package com.ares.hadoop.mr.flowsum; import java.io.IOException; import org.apache. ...
- scrapy爬虫 函数间传值简易教程
2017-03-27 有的时候我们爬取数据的时候需要在多个页面之间跳转,爬取完所有页面的数据的时候才能把所有数据一起存到数据库,这个时候我们就需要把某个函数内爬取的数据传到下一个函数当中.有人可能会说 ...