The feature extractor with customized methods on the python-side. More...

#include <feature_extractor.h>

Inheritance diagram for tvm::s_tir::meta_schedule::PyFeatureExtractorObj:

Collaboration diagram for tvm::s_tir::meta_schedule::PyFeatureExtractorObj:

Public Types
using	FExtractFrom = ffi::TypedFunction< ffi::Array< tvm::ffi::Tensor >(const TuneContext &context, const ffi::Array< MeasureCandidate > &candidates)>
	Extract features from the given measure candidate.

Public Member Functions
ffi::Array< tvm::ffi::Tensor >	ExtractFrom (const TuneContext &context, const ffi::Array< MeasureCandidate > &candidates) final
	Extract features from the given measure candidate.

	TVM_FFI_DECLARE_OBJECT_INFO_FINAL ("s_tir.meta_schedule.PyFeatureExtractor", PyFeatureExtractorObj, FeatureExtractorObj)

Public Member Functions inherited from tvm::s_tir::meta_schedule::FeatureExtractorObj
virtual	~FeatureExtractorObj ()=default
	Virtual destructor.

	TVM_FFI_DECLARE_OBJECT_INFO ("s_tir.meta_schedule.FeatureExtractor", FeatureExtractorObj, ffi::Object)

Static Public Member Functions
static void	RegisterReflection ()

Static Public Member Functions inherited from tvm::s_tir::meta_schedule::FeatureExtractorObj
static void	RegisterReflection ()

Public Attributes
FExtractFrom	f_extract_from
	The packed function to the `ExtractFrom` function.

Detailed Description

The feature extractor with customized methods on the python-side.

Member Typedef Documentation

◆ FExtractFrom

using tvm::s_tir::meta_schedule::PyFeatureExtractorObj::FExtractFrom = ffi::TypedFunction<ffi::Array<tvm::ffi::Tensor>( const TuneContext& context, const ffi::Array<MeasureCandidate>& candidates)>

Extract features from the given measure candidate.

Parameters

context	The tuning context for feature extraction.
candidates	The measure candidates to extract features from.

Returns: The feature tensor extracted.

Member Function Documentation

◆ ExtractFrom()

ffi::Array< tvm::ffi::Tensor > tvm::s_tir::meta_schedule::PyFeatureExtractorObj::ExtractFrom	(	const TuneContext &	context,
		const ffi::Array< MeasureCandidate > &	candidates
	)

finalvirtual

Extract features from the given measure candidate.

Parameters

context	The tuning context for feature extraction.
candidates	The measure candidates to extract features from.

Returns: The feature tensor extracted.

Implements tvm::s_tir::meta_schedule::FeatureExtractorObj.

◆ RegisterReflection()

static void tvm::s_tir::meta_schedule::PyFeatureExtractorObj::RegisterReflection ( )

inlinestatic

◆ TVM_FFI_DECLARE_OBJECT_INFO_FINAL()

tvm::s_tir::meta_schedule::PyFeatureExtractorObj::TVM_FFI_DECLARE_OBJECT_INFO_FINAL	(	"s_tir.meta_schedule.PyFeatureExtractor"	,
		PyFeatureExtractorObj	,
		FeatureExtractorObj
	)

Member Data Documentation

◆ f_extract_from

FExtractFrom tvm::s_tir::meta_schedule::PyFeatureExtractorObj::f_extract_from

The packed function to the ExtractFrom function.

The documentation for this class was generated from the following file:

include/tvm/s_tir/meta_schedule/feature_extractor.h

Public Types

Public Member Functions

Static Public Member Functions

Public Attributes