#include 
#include 

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

namespace caffe {

template 
void Blob::Reshape(const int num, const int channels, const int height,
    const int width) {
  vector shape(4);
  shape[0] = num;
  shape[1] = channels;
  shape[2] = height;
  shape[3] = width;
  Reshape(shape);
}

template 
void Blob::Reshape(const vector& shape) {
  CHECK_LE(shape.size(), kMaxBlobAxes);
  count_ = 1;
  shape_.resize(shape.size());
  if (!shape_data_ || shape_data_->size() < shape.size() * sizeof(int)) {
    shape_data_.reset(new SyncedMemory(shape.size() * sizeof(int)));
  }
  int* shape_data = static_cast(shape_data_->mutable_cpu_data());
  for (int i = 0; i < shape.size(); ++i) {
    CHECK_GE(shape[i], 0);
    if (count_ != 0) {
      CHECK_LE(shape[i], INT_MAX / count_)  capacity_) {
    capacity_ = count_;
    data_.reset(new SyncedMemory(capacity_ * sizeof(Dtype)));
    diff_.reset(new SyncedMemory(capacity_ * sizeof(Dtype)));
  }
}

template 
void Blob::Reshape(const BlobShape& shape) {
  CHECK_LE(shape.dim_size(), kMaxBlobAxes);
  vector shape_vec(shape.dim_size());
  for (int i = 0; i < shape.dim_size(); ++i) {
    shape_vec[i] = shape.dim(i);
  }
  Reshape(shape_vec);
}

template 
void Blob::ReshapeLike(const Blob& other) {
  Reshape(other.shape());
}

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

template 
const int* Blob::gpu_shape() const {
  CHECK(shape_data_);
  return (const int*)shape_data_->gpu_data();
}

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

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

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

template 
const Dtype* Blob::gpu_diff() const {
  CHECK(diff_);
  return (const Dtype*)diff_->gpu_data();
}

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

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

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

template 
Dtype* Blob::mutable_gpu_diff() {
  CHECK(diff_);
  return static_cast(diff_->mutable_gpu_data());
}

template 
void Blob::ShareData(const Blob& other) {
  CHECK_EQ(count_, other.count());
  data_ = other.data();
}

template 
void Blob::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 or Blob -- hence we do not define it for
// Blob or Blob.
template  void Blob::Update() { NOT_IMPLEMENTED; }
template  void Blob::Update() { NOT_IMPLEMENTED; }

template 
void Blob::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(count_, Dtype(-1),
        static_cast(diff_->cpu_data()),
        static_cast(data_->mutable_cpu_data()));
    break;
  case SyncedMemory::HEAD_AT_GPU:
  case SyncedMemory::SYNCED:
#ifndef CPU_ONLY
    // perform computation on GPU
    caffe_gpu_axpy(count_, Dtype(-1),
        static_cast(diff_->gpu_data()),
        static_cast(data_->mutable_gpu_data()));
#else
    NO_GPU;
#endif
    break;
  default:
    LOG(FATAL) 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) 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) 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) 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) 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) 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) mutable_cpu_data()));
    } else {
      caffe_copy(count_, source.cpu_data(),
          static_cast(data_->mutable_cpu_data()));
    }
    break;
  default:
    LOG(FATAL)  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::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::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;
template class Blob;

}  // namespace caffe