#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);
CHECK_LE(shape[i], INT_MAX / count_) << "blob size exceeds INT_MAX";
count_ *= shape[i];
shape_[i] = shape[i];
shape_data[i] = shape[i];
}
if (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);
data_->set_cpu_data(data);
}
template
const Dtype* Blob::gpu_data() const {
CHECK(data_);
return (const Dtype*)data_->gpu_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) << "Syncedmem not initialized.";
}
}
template <> unsigned int Blob::asum_data() const {
NOT_IMPLEMENTED;
return 0;
}
template <> int Blob::asum_data() const {
NOT_IMPLEMENTED;
return 0;
}
template
Dtype Blob::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::asum_diff() const {
NOT_IMPLEMENTED;
return 0;
}
template <> int Blob::asum_diff() const {
NOT_IMPLEMENTED;
return 0;
}
template
Dtype Blob::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::sumsq_data() const {
NOT_IMPLEMENTED;
return 0;
}
template <> int Blob::sumsq_data() const {
NOT_IMPLEMENTED;
return 0;
}
template
Dtype Blob::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::sumsq_diff() const {
NOT_IMPLEMENTED;
return 0;
}
template <> int Blob::sumsq_diff() const {
NOT_IMPLEMENTED;
return 0;
}
template
Dtype Blob::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::scale_data(unsigned int scale_factor) {
NOT_IMPLEMENTED;
}
template <> void Blob::scale_data(int scale_factor) {
NOT_IMPLEMENTED;
}
template
void Blob::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::scale_diff(unsigned int scale_factor) {
NOT_IMPLEMENTED;
}
template <> void Blob::scale_diff(int scale_factor) {
NOT_IMPLEMENTED;
}
template
void Blob::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();
}
}
template
bool Blob::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 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;
}
template
void Blob::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(diff_->mutable_gpu_data()));
} else {
caffe_copy(count_, source.gpu_data(),
static_cast(data_->mutable_gpu_data()));
}
break;
case Caffe::CPU:
if (copy_diff) {
caffe_copy(count_, source.cpu_diff(),
static_cast(diff_->mutable_cpu_data()));
} else {
caffe_copy(count_, source.cpu_data(),
static_cast(data_->mutable_cpu_data()));
}
break;
default:
LOG(FATAL) << "Unknown caffe mode.";
}
}
template
void Blob::FromProto(const BlobProto& proto, bool reshape) {
if (reshape) {
vector 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);
}
}
}
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