Caffe学习系列（17）： blob

对于blob.h文件。

先看成员变量。定义了6个保护的成员变量，包括前、后向传播的数据，新、旧形状数据（？），

数据个数及容量。

再看成员函数。包括构造函数（4个参数），reshape（改变blob形状），以及很多inline函数。

#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>//老方法调用新方法
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);//是否小于规定的最大BLOB的维度(35维)
count_ = 1;
shape_.resize(shape.size());//将旧的数据大小置为新的数据大小
if (!shape_data_ || shape_data_->size() < shape.size() * sizeof(int)) {
//shape_和shape_data_的区别就在于后者分配了空间（有什么用呢？）
shape_data_.reset(new SyncedMemory(shape.size() * sizeof(int)));
}
int* shape_data = static_cast<int*>(shape_data_->mutable_cpu_data());
for (int i = 0; i < shape.size(); ++i) {
CHECK_GE(shape[i], 0);//检查数据是否合法
if (count_ != 0) {
CHECK_LE(shape[i], INT_MAX / count_) << "blob size exceeds INT_MAX";
}
count_ *= shape[i];//数据个数
shape_[i] = shape[i];//复制shape到新的和旧的形状数据
shape_data[i] = shape[i];
}
if (count_ > capacity_) {//如果超过了容量，重新分配内存
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_ must be initialized before calling Reshape
: capacity_(0) {
Reshape(num, channels, height, width);
}

template <typename Dtype>
Blob<Dtype>::Blob(const vector<int>& shape)
// capacity_ must be initialized before calling Reshape
: capacity_(0) {
Reshape(shape);
}

template <typename Dtype>
const int* Blob<Dtype>::gpu_shape() const {
CHECK(shape_data_);
return (const int*)shape_data_->gpu_data();
}
//得到data
template <typename Dtype>
const Dtype* Blob<Dtype>::cpu_data() const {
CHECK(data_);
return (const Dtype*)data_->cpu_data();
}
//设置data
template <typename Dtype>
void Blob<Dtype>::set_cpu_data(Dtype* data) {
CHECK(data);
// Make sure CPU and GPU sizes remain equal
size_t size = count_ * sizeof(Dtype);
if (data_->size() != size) {
data_.reset(new SyncedMemory(size));
diff_.reset(new SyncedMemory(size));
}
data_->set_cpu_data(data);
}

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

template <typename Dtype>
void Blob<Dtype>::set_gpu_data(Dtype* data) {
CHECK(data);
// Make sure CPU and GPU sizes remain equal
size_t size = count_ * sizeof(Dtype);
if (data_->size() != size) {
data_.reset(new SyncedMemory(size));
diff_.reset(new SyncedMemory(size));
}
data_->set_gpu_data(data);
}

template <typename Dtype>
const Dtype* Blob<Dtype>::cpu_diff() const {
CHECK(diff_);
return (const Dtype*)diff_->cpu_data();
}

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());
}
//关键字mutable，变量被其修饰时，即使函数为const也能修改之
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());
}
//复制blob
template <typename Dtype>
void Blob<Dtype>::ShareData(const Blob& other) {
CHECK_EQ(count_, other.count());
data_ = other.data();
}

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; }
//更新 根据data_的head来更新，更新为data=-1*diff+data
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:
// 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
// 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;
}

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;
}
//计算data的L1范数
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;
}
//L2范数
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 = 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 <typename Dtype>
Dtype Blob<Dtype>::sumsq_diff() const {
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;
}
//将data部分乘一个因子
template <typename Dtype>
void Blob<Dtype>::scale_data(Dtype scale_factor) {
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 <typename Dtype>
void Blob<Dtype>::scale_diff(Dtype scale_factor) {
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();
}
}
//两个blob的shape是否一样
template <typename Dtype>
bool Blob<Dtype>::ShapeEquals(const BlobProto& other) {
if (other.has_num() || other.has_channels() ||
other.has_height() || other.has_width()) {//判断是否是旧的blob（为何能判断？）
// Using deprecated 4D Blob dimensions --
// shape is (num, channels, height, width).
// Note: we do not use the normal Blob::num(), Blob::channels(), etc.
// methods as these index from the beginning of the blob shape, where legacy
// parameter blobs were indexed from the end of the blob shape (e.g., bias
// Blob shape (1 x 1 x 1 x N), IP layer weight Blob shape (1 x 1 x M x N)).
return shape_.size() <= 4 &&
LegacyShape(-4) == other.num() &&
LegacyShape(-3) == other.channels() &&
LegacyShape(-2) == other.height() &&
LegacyShape(-1) == other.width();
}
//不是则复制判断
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;
}
//复制diff和data
template <typename Dtype>
void Blob<Dtype>::CopyFrom(const Blob& source, bool copy_diff, bool reshape) {
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) {
if (reshape) {
vector<int> shape;
if (proto.has_num() || proto.has_channels() || //如果是旧的blob则直接转为新的blob中的数据
proto.has_height() || proto.has_width()) {
// Using deprecated 4D Blob dimensions --
// shape is (num, channels, height, 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)";
}
// copy data复制data和diff
Dtype* data_vec = mutable_cpu_data();//获取当前数据的互斥指针
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 {
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<int>;
template class Blob<unsigned int>;

}  // namespace caffe

View Code
Blob：4个维度 n x c x h x w；

bottom[0] 、bottom[1]代表该层有几个输入。

bottom[0]->count(): 输入中，元素的总维数（个数）

bottom[0]->nums(): 输入中，块（block）的个数，该参数还对应batch_size,即同时输入了几张图片
c：是卷积核（filter）的个数，每个卷积核产生一个通道的输出；在输入层，c直接就是图像的通道数；
还有一个变量，dim;：每个块的维度（元素个数）

形象化：
| xxxxx | xxxxx | xxxxx | xxxxx | xxxxx | xxxxx | xxxxx | xxxxx |

上图，nums = 8， dim = 5， count = 5*8 =40；

参考：http://blog.csdn.net/qq_14975217/article/details/51524042
http://blog.csdn.net/xizero00/article/details/50886829 http://www.cnblogs.com/louyihang-loves-baiyan/p/5149628.html
关于常见的BLAS函数，参考：http://www.cnblogs.com/huashiyiqike/p/3886670.html

关于protobuf，参考：https://www.ibm.com/developerworks/cn/linux/l-cn-gpb/