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

Refactor configuration [Part II]. (#4577)

Browse Source 
* Refactor configuration [Part II].

* General changes:
** Remove `Init` methods to avoid ambiguity.
** Remove `Configure(std::map<>)` to avoid redundant copying and prepare for
   parameter validation. (`std::vector` is returned from `InitAllowUnknown`).
** Add name to tree updaters for easier debugging.

* Learner changes:
** Make `LearnerImpl` the only source of configuration.

    All configurations are stored and carried out by `LearnerImpl::Configure()`.

** Remove booster in C API.

    Originally kept for "compatibility reason", but did not state why.  So here
    we just remove it.

** Add a `metric_names_` field in `LearnerImpl`.
** Remove `LazyInit`.  Configuration will always be lazy.
** Run `Configure` before every iteration.

* Predictor changes:
** Allocate both cpu and gpu predictor.
** Remove cpu_predictor from gpu_predictor.

    `GBTree` is now used to dispatch the predictor.

** Remove some GPU Predictor tests.

* IO

No IO changes.  The binary model format stability is tested by comparing
hashing value of save models between two commits
This commit is contained in:
Jiaming Yuan
2019-07-20 08:34:56 -04:00
committed by GitHub
parent ad1192e8a3
commit f0064c07ab
69 changed files with 669 additions and 761 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/tree/split_evaluator.cc
View File

@@ -43,8 +43,7 @@ SplitEvaluator* SplitEvaluator::Create(const std::string& name) {
}
// Default implementations of some virtual methods that aren't always needed
void SplitEvaluator::Init(
const std::vector<std::pair<std::string, std::string> >& args) {}
void SplitEvaluator::Init(const Args& args) {}
void SplitEvaluator::Reset() {}
void SplitEvaluator::AddSplit(bst_uint nodeid,
bst_uint leftid,
@@ -104,8 +103,7 @@ class ElasticNet final : public SplitEvaluator {
LOG(FATAL) << "ElasticNet does not accept an inner SplitEvaluator";
}
}
void Init(
const std::vector<std::pair<std::string, std::string> >& args) override {
void Init(const Args& args) override {
params_.InitAllowUnknown(args);
}
@@ -210,7 +208,7 @@ class MonotonicConstraint final : public SplitEvaluator {
inner_ = std::move(inner);
}
void Init(const std::vector<std::pair<std::string, std::string> >& args)
void Init(const Args& args)
override {
inner_->Init(args);
params_.InitAllowUnknown(args);
@@ -369,7 +367,7 @@ class InteractionConstraint final : public SplitEvaluator {
inner_ = std::move(inner);
}
void Init(const std::vector<std::pair<std::string, std::string> >& args)
void Init(const Args& args)
override {
inner_->Init(args);
params_.InitAllowUnknown(args);

3
src/tree/split_evaluator.h
View File

@@ -32,8 +32,7 @@ class SplitEvaluator {
virtual ~SplitEvaluator() = default;
// Used to initialise any regularisation hyperparameters provided by the user
virtual void Init(
const std::vector<std::pair<std::string, std::string> >& args);
virtual void Init(const Args& args);
// Resets the SplitEvaluator to the state it was in after the Init was called
virtual void Reset();

2
src/tree/tree_updater.cc
View File

@@ -14,7 +14,7 @@ DMLC_REGISTRY_ENABLE(::xgboost::TreeUpdaterReg);
namespace xgboost {
TreeUpdater* TreeUpdater::Create(const std::string& name, LearnerTrainParam const* tparam) {
TreeUpdater* TreeUpdater::Create(const std::string& name, GenericParameter const* tparam) {
auto *e = ::dmlc::Registry< ::xgboost::TreeUpdaterReg>::Get()->Find(name);
if (e == nullptr) {
LOG(FATAL) << "Unknown tree updater " << name;

2
src/tree/updater_basemaker-inl.h
View File

@@ -30,7 +30,7 @@ namespace tree {
*/
class BaseMaker: public TreeUpdater {
public:
void Init(const std::vector<std::pair<std::string, std::string> >& args) override {
void Configure(const Args& args) override {
param_.InitAllowUnknown(args);
}

15
src/tree/updater_colmaker.cc
View File

@@ -25,12 +25,16 @@ DMLC_REGISTRY_FILE_TAG(updater_colmaker);
/*! \brief column-wise update to construct a tree */
class ColMaker: public TreeUpdater {
public:
void Init(const std::vector<std::pair<std::string, std::string> >& args) override {
void Configure(const Args& args) override {
param_.InitAllowUnknown(args);
spliteval_.reset(SplitEvaluator::Create(param_.split_evaluator));
spliteval_->Init(args);
}
char const* Name() const override {
return "grow_colmaker";
}
void Update(HostDeviceVector<GradientPair> *gpair,
DMatrix* dmat,
const std::vector<RegTree*> &trees) override {
@@ -768,13 +772,18 @@ class ColMaker: public TreeUpdater {
// distributed column maker
class DistColMaker : public ColMaker {
public:
void Init(const std::vector<std::pair<std::string, std::string> >& args) override {
void Configure(const Args& args) override {
param_.InitAllowUnknown(args);
pruner_.reset(TreeUpdater::Create("prune", tparam_));
pruner_->Init(args);
pruner_->Configure(args);
spliteval_.reset(SplitEvaluator::Create(param_.split_evaluator));
spliteval_->Init(args);
}
char const* Name() const override {
return "distcol";
}
void Update(HostDeviceVector<GradientPair> *gpair,
DMatrix* dmat,
const std::vector<RegTree*> &trees) override {

6
src/tree/updater_gpu.cu
View File

@@ -581,7 +581,11 @@ class GPUMaker : public TreeUpdater {
GPUMaker() : allocated_{false} {}
~GPUMaker() override = default;
void Init(const std::vector<std::pair<std::string, std::string>> &args) override {
char const* Name() const override {
return "gpu_exact";
}
void Configure(const Args &args) override {
param_.InitAllowUnknown(args);
maxNodes_ = (1 << (param_.max_depth + 1)) - 1;
maxLeaves_ = 1 << param_.max_depth;

2
src/tree/updater_gpu_common.cuh
View File

@@ -1,5 +1,5 @@
/*!
* Copyright 2017 XGBoost contributors
* Copyright 2017-2019 XGBoost contributors
*/
#pragma once
#include <thrust/random.h>

24
src/tree/updater_gpu_hist.cu
View File

@@ -1290,13 +1290,12 @@ template <typename GradientSumT>
class GPUHistMakerSpecialised {
public:
GPUHistMakerSpecialised() : initialised_{false}, p_last_fmat_{nullptr} {}
void Init(const std::vector<std::pair<std::string, std::string>>& args,
LearnerTrainParam const* lparam) {
void Configure(const Args& args, GenericParameter const* generic_param) {
param_.InitAllowUnknown(args);
learner_param_ = lparam;
generic_param_ = generic_param;
hist_maker_param_.InitAllowUnknown(args);
auto devices = GPUSet::All(learner_param_->gpu_id,
learner_param_->n_gpus);
auto devices = GPUSet::All(generic_param_->gpu_id,
generic_param_->n_gpus);
n_devices_ = devices.Size();
CHECK(n_devices_ != 0) << "Must have at least one device";
dist_ = GPUDistribution::Block(devices);
@@ -1362,7 +1361,7 @@ class GPUHistMakerSpecialised {
monitor_.StartCuda("Quantiles");
// Create the quantile sketches for the dmatrix and initialize HistogramCuts
size_t row_stride = common::DeviceSketch(param_, *learner_param_,
size_t row_stride = common::DeviceSketch(param_, *generic_param_,
hist_maker_param_.gpu_batch_nrows,
dmat, &hmat_);
monitor_.StopCuda("Quantiles");
@@ -1488,7 +1487,7 @@ class GPUHistMakerSpecialised {
int n_bins_;
GPUHistMakerTrainParam hist_maker_param_;
LearnerTrainParam const* learner_param_;
GenericParameter const* generic_param_;
dh::AllReducer reducer_;
@@ -1502,17 +1501,16 @@ class GPUHistMakerSpecialised {
class GPUHistMaker : public TreeUpdater {
public:
void Init(
const std::vector<std::pair<std::string, std::string>>& args) override {
void Configure(const Args& args) override {
hist_maker_param_.InitAllowUnknown(args);
float_maker_.reset();
double_maker_.reset();
if (hist_maker_param_.single_precision_histogram) {
float_maker_.reset(new GPUHistMakerSpecialised<GradientPair>());
float_maker_->Init(args, tparam_);
float_maker_->Configure(args, tparam_);
} else {
double_maker_.reset(new GPUHistMakerSpecialised<GradientPairPrecise>());
double_maker_->Init(args, tparam_);
double_maker_->Configure(args, tparam_);
}
}
@@ -1534,6 +1532,10 @@ class GPUHistMaker : public TreeUpdater {
}
}
char const* Name() const override {
return "gpu_hist";
}
private:
GPUHistMakerTrainParam hist_maker_param_;
std::unique_ptr<GPUHistMakerSpecialised<GradientPair>> float_maker_;

17
src/tree/updater_histmaker.cc
View File

@@ -33,6 +33,9 @@ class HistMaker: public BaseMaker {
}
param_.learning_rate = lr;
}
char const* Name() const override {
return "grow_histmaker";
}
protected:
/*! \brief a single histogram */
@@ -83,7 +86,7 @@ class HistMaker: public BaseMaker {
// per thread histset
std::vector<HistSet> hset;
// initialize the hist set
inline void Init(const TrainParam &param, int nthread) {
inline void Configure(const TrainParam &param, int nthread) {
hset.resize(nthread);
// cleanup statistics
for (int tid = 0; tid < nthread; ++tid) {
@@ -274,6 +277,9 @@ class HistMaker: public BaseMaker {
class CQHistMaker: public HistMaker {
public:
CQHistMaker() = default;
char const* Name() const override {
return "grow_local_histmaker";
}
protected:
struct HistEntry {
@@ -339,7 +345,7 @@ class CQHistMaker: public HistMaker {
feat2workindex_[fset[i]] = static_cast<int>(i);
}
// start to work
this->wspace_.Init(this->param_, 1);
this->wspace_.Configure(this->param_, 1);
// if it is C++11, use lazy evaluation for Allreduce,
// to gain speedup in recovery
auto lazy_get_hist = [&]() {
@@ -637,6 +643,11 @@ class CQHistMaker: public HistMaker {
// global proposal
class GlobalProposalHistMaker: public CQHistMaker {
public:
char const* Name() const override {
return "grow_global_histmaker";
}
protected:
void ResetPosAndPropose(const std::vector<GradientPair> &gpair,
DMatrix *p_fmat,
@@ -682,7 +693,7 @@ class GlobalProposalHistMaker: public CQHistMaker {
this->feat2workindex_[fset[i]] = static_cast<int>(i);
}
// start to work
this->wspace_.Init(this->param_, 1);
this->wspace_.Configure(this->param_, 1);
// to gain speedup in recovery
{
this->thread_hist_.resize(omp_get_max_threads());

8
src/tree/updater_prune.cc
View File

@@ -24,10 +24,14 @@ class TreePruner: public TreeUpdater {
TreePruner() {
syncher_.reset(TreeUpdater::Create("sync", tparam_));
}
char const* Name() const override {
return "prune";
}
// set training parameter
void Init(const std::vector<std::pair<std::string, std::string> >& args) override {
void Configure(const Args& args) override {
param_.InitAllowUnknown(args);
syncher_->Init(args);
syncher_->Configure(args);
}
// update the tree, do pruning
void Update(HostDeviceVector<GradientPair> *gpair,

4
src/tree/updater_quantile_hist.cc
View File

@@ -32,12 +32,12 @@ namespace tree {
DMLC_REGISTRY_FILE_TAG(updater_quantile_hist);
void QuantileHistMaker::Init(const std::vector<std::pair<std::string, std::string> >& args) {
void QuantileHistMaker::Configure(const Args& args) {
// initialize pruner
if (!pruner_) {
pruner_.reset(TreeUpdater::Create("prune", tparam_));
}
pruner_->Init(args);
pruner_->Configure(args);
param_.InitAllowUnknown(args);
is_gmat_initialized_ = false;

5
src/tree/updater_quantile_hist.h
View File

@@ -46,7 +46,7 @@ using xgboost::common::Column;
/*! \brief construct a tree using quantized feature values */
class QuantileHistMaker: public TreeUpdater {
public:
void Init(const std::vector<std::pair<std::string, std::string> >& args) override;
void Configure(const Args& args) override;
void Update(HostDeviceVector<GradientPair>* gpair,
DMatrix* dmat,
@@ -55,6 +55,9 @@ class QuantileHistMaker: public TreeUpdater {
bool UpdatePredictionCache(const DMatrix* data,
HostDeviceVector<bst_float>* out_preds) override;
char const* Name() const override {
return "grow_quantile_histmaker";
}
protected:
// training parameter

5
src/tree/updater_refresh.cc
View File

@@ -21,9 +21,12 @@ DMLC_REGISTRY_FILE_TAG(updater_refresh);
/*! \brief pruner that prunes a tree after growing finishs */
class TreeRefresher: public TreeUpdater {
public:
void Init(const std::vector<std::pair<std::string, std::string> >& args) override {
void Configure(const Args& args) override {
param_.InitAllowUnknown(args);
}
char const* Name() const override {
return "refresh";
}
// update the tree, do pruning
void Update(HostDeviceVector<GradientPair> *gpair,
DMatrix *p_fmat,

3
src/tree/updater_skmaker.cc
View File

@@ -22,6 +22,9 @@ DMLC_REGISTRY_FILE_TAG(updater_skmaker);
class SketchMaker: public BaseMaker {
public:
char const* Name() const override {
return "grow_skmaker";
}
void Update(HostDeviceVector<GradientPair> *gpair,
DMatrix *p_fmat,
const std::vector<RegTree*> &trees) override {

6
src/tree/updater_sync.cc
View File

@@ -20,7 +20,11 @@ DMLC_REGISTRY_FILE_TAG(updater_sync);
*/
class TreeSyncher: public TreeUpdater {
public:
void Init(const std::vector<std::pair<std::string, std::string> >& args) override {}
void Configure(const Args& args) override {}
char const* Name() const override {
return "prune";
}
void Update(HostDeviceVector<GradientPair> *gpair,
DMatrix* dmat,