Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Convert labels into tensor. (#7456)

Browse Source 
* Add a new ctor to tensor for `initilizer_list`.
* Change labels from host device vector to tensor.
* Rename the field from `labels_` to `labels` since it's a public member.
This commit is contained in:
Jiaming Yuan
2021-12-17 00:58:35 +08:00
committed by GitHub
parent 6f8a4633b7
commit 5b1161bb64
35 changed files with 319 additions and 258 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
include/xgboost/data.h
View File

@@ -56,7 +56,7 @@ class MetaInfo {
/*! \brief number of nonzero entries in the data */
uint64_t num_nonzero_{0}; // NOLINT
/*! \brief label of each instance */
HostDeviceVector<bst_float> labels_; // NOLINT
linalg::Tensor<float, 2> labels;
/*!
* \brief the index of begin and end of a group
* needed when the learning task is ranking.
@@ -119,12 +119,12 @@ class MetaInfo {
}
/*! \brief get sorted indexes (argsort) of labels by absolute value (used by cox loss) */
inline const std::vector<size_t>& LabelAbsSort() const {
if (label_order_cache_.size() == labels_.Size()) {
if (label_order_cache_.size() == labels.Size()) {
return label_order_cache_;
}
label_order_cache_.resize(labels_.Size());
label_order_cache_.resize(labels.Size());
std::iota(label_order_cache_.begin(), label_order_cache_.end(), 0);
const auto& l = labels_.HostVector();
const auto& l = labels.Data()->HostVector();
XGBOOST_PARALLEL_SORT(label_order_cache_.begin(), label_order_cache_.end(),
[&l](size_t i1, size_t i2) {return std::abs(l[i1]) < std::abs(l[i2]);});

46
include/xgboost/linalg.h
View File

@@ -635,6 +635,20 @@ class Tensor {
HostDeviceVector<T> data_;
ShapeT shape_{0};
template <typename I, std::int32_t D>
void Initialize(I const (&shape)[D], std::int32_t device) {
static_assert(D <= kDim, "Invalid shape.");
std::copy(shape, shape + D, shape_);
for (auto i = D; i < kDim; ++i) {
shape_[i] = 1;
}
if (device >= 0) {
data_.SetDevice(device);
data_.DevicePointer(); // Pull to device;
}
CHECK_EQ(data_.Size(), detail::CalcSize(shape_));
}
public:
Tensor() = default;
@@ -665,20 +679,20 @@ class Tensor {
*/
template <typename It, typename I, int32_t D>
explicit Tensor(It begin, It end, I const (&shape)[D], int32_t device) {
// shape
static_assert(D <= kDim, "Invalid shape.");
std::copy(shape, shape + D, shape_);
for (auto i = D; i < kDim; ++i) {
shape_[i] = 1;
}
auto &h_vec = data_.HostVector();
h_vec.insert(h_vec.begin(), begin, end);
if (device >= 0) {
data_.SetDevice(device);
data_.DevicePointer(); // Pull to device;
}
CHECK_EQ(data_.Size(), detail::CalcSize(shape_));
// shape
this->Initialize(shape, device);
}
template <typename I, int32_t D>
explicit Tensor(std::initializer_list<T> data, I const (&shape)[D], int32_t device) {
auto &h_vec = data_.HostVector();
h_vec = data;
// shape
this->Initialize(shape, device);
}
/**
* \brief Get a \ref TensorView for this tensor.
*/
@@ -703,6 +717,9 @@ class Tensor {
}
}
auto HostView() const { return this->View(-1); }
auto HostView() { return this->View(-1); }
size_t Size() const { return data_.Size(); }
auto Shape() const { return common::Span<size_t const, kDim>{shape_}; }
auto Shape(size_t i) const { return shape_[i]; }
@@ -756,14 +773,15 @@ class Tensor {
/**
* \brief Set device ordinal for this tensor.
*/
void SetDevice(int32_t device) { data_.SetDevice(device); }
void SetDevice(int32_t device) const { data_.SetDevice(device); }
int32_t DeviceIdx() const { return data_.DeviceIdx(); }
};
// Only first axis is supported for now.
template <typename T, int32_t D>
void Stack(Tensor<T, D> *l, Tensor<T, D> const &r) {
if (r.Data()->DeviceIdx() >= 0) {
l->Data()->SetDevice(r.Data()->DeviceIdx());
if (r.DeviceIdx() >= 0) {
l->SetDevice(r.DeviceIdx());
}
l->ModifyInplace([&](HostDeviceVector<T> *data, common::Span<size_t, D> shape) {
for (size_t i = 1; i < D; ++i) {