caffe源码 Blob.cpp 详解

caffe数据块是整个框架的基础部分，了解其结构特点对了解框架特点抑或自己开发新层是十分必要的。  
  
其blob.hpp主要是进行了一些：声明、类函数inline内嵌、简单函数定义等，不是很复杂。  
  

因此主要介绍其cpp模块。

#include <climits>
#include <vector>

#include "caffe/blob.hpp"
#include "caffe/common.hpp"
#include "caffe/syncedmem.hpp"
#include "caffe/util/math_functions.hpp"

namespace caffe {
//定义caffe命名空间，有利于避免命名冲突，因此创建caffe作用域。
//各种Blob<Dtype>::Reshape都是为了进行blob类的初始化构造。
//这里泛型编程，便于适应各种不同的数据类型的输入，Dtype为泛型类型，无具体类型，
//根据输入类型决定具体类型，增强函数复用性。
template <typename Dtype>
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);
}
//这里的各种Blob<Dtype>::Reshape都是为了将各种不同类型的输入转成  
//下面这个Blob<Dtype>::Reshape需要的vector<int>&类型，就像{48,3,128,128}。
//这里插一句，这又是泛型编程又是+&转别名输入，才让函数/类的输入可以像python一样。
template <typename Dtype>
void Blob<Dtype>::Reshape(const vector<int>& shape) {
  CHECK_LE(shape.size(), kMaxBlobAxes);//检查形状维度数没有超过最大支持维度数32
  count_ = 1;//初始化成员变量
  shape_.resize(shape.size());//调整shape_（const vector<int>&）的维度数和输入的一样
  //若shape_data_（shared_ptr智能指针）未分配内存资源，
  //或者其指向的形状数据内存小于输入shape的形状数据大小。
  if (!shape_data_ || shape_data_->size() < shape.size() * sizeof(int)) {
    //重新为shared_ptr智能指针赋值并为其分配shape大小的内存空间。
    shape_data_.reset(new SyncedMemory(shape.size() * sizeof(int)));
  }
  //强制类型转换，转换成指向int数据类型指针
  int* shape_data = static_cast<int*>(shape_data_->mutable_cpu_data());
  //逐个维度检查对应形状大小是否超出int描述能力，并累乘计算占的空间count_
  for (int i = 0; i < shape.size(); ++i) {
    CHECK_GE(shape[i], 0);
    if (count_ != 0) {
      CHECK_LE(shape[i], INT_MAX / count_) << "blob size exceeds INT_MAX";
    }
    count_ *= shape[i];
    shape_[i] = shape[i];//形状数据，vector<int>类型
    shape_data[i] = shape[i];//形状数据指针
  }
  //之前分配的空间不足时，重新分配内存空间。
  if (count_ > capacity_) {
    capacity_ = count_;
    //这里的data_,diff_都是shared_ptr，通过reset的方式来重新赋值，开辟新的动态内存空间给blob
    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因为会被用到判断
  : 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);
}
//获取blob在gpu上存储数据形状的指针，const限定无法通过这一指针修改该数据
template <typename Dtype>
const int* Blob<Dtype>::gpu_shape() const {
  CHECK(shape_data_);
  return (const int*)shape_data_->gpu_data();
}

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

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());
}
//将data_和diff_都换成别的blob的数据
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>.
//update是为net中的参数blob准备的，只有float或double，不支持int和unsigned int
template <> void Blob<unsigned int>::Update() { NOT_IMPLEMENTED; }
template <> void Blob<int>::Update() { NOT_IMPLEMENTED; }

template <typename Dtype>
void Blob<Dtype>::Update() {
  // We will perform update based on where the data is located.
  //进行参数更新-1 * diff + w，支持double和float，这个函数在utll/math_functions.cpp里
  //template <>
  //void caffe_axpy<float>(const int N, const float alpha, const float* X,
      //float* Y) { cblas_saxpy(N, alpha, X, 1, Y, 1); }
  //template <>
  //void caffe_axpy<double>(const int N, const double alpha, const double* X,
      //double* Y) { cblas_daxpy(N, alpha, X, 1, Y, 1); }
  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.";
  }
}
//下面的程序计算L1，L2范数以及scale函数，都在mathfunction里。
//同样不支持uint 和int类型
template <> unsigned int Blob<unsigned int>::asum_data() const {
  NOT_IMPLEMENTED;
  return 0;
}

template <> int Blob<int>::asum_data() const {
  NOT_IMPLEMENTED;
  return 0;
}
//还是调用caffe_cpu_asum函数在utll/math_functions.cpp计算每个值的绝对值加和
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;
}

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;
}

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;
}

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();
  }
}
//判断形状是否相等
template <typename Dtype>
bool Blob<Dtype>::ShapeEquals(const BlobProto& other) {
  if (other.has_num() || other.has_channels() ||
      other.has_height() || other.has_width()) {
    // 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();
  }
  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;
}
//从其他blob拷贝数据，由copy_diff=False拷贝data，否则拷贝diff
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.";
  }
}
//resize成protobuf中对应形状，并从proto读取data和diff
template <typename Dtype>
void Blob<Dtype>::FromProto(const BlobProto& proto, bool reshape) {
  if (reshape) {
    vector<int> shape;
    if (proto.has_num() || proto.has_channels() ||
        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
  Dtype* data_vec = mutable_cpu_data();
  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);
    }
  }
}
//下面两个分别写double和float的blob到protobuf里
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