MLLIB::MlModel Class Reference

Backend-agnostic inference interface: load, predict, save plus model/task descriptors. More...

#include <ml_model.h>

Public Types
typedef QSharedPointer< MlModel >	SPtr

Public Member Functions
virtual	~MlModel ()=default
virtual MlTensor	predict (const MlTensor &input) const =0
virtual bool	save (const QString &path) const =0
virtual bool	load (const QString &path)=0
virtual QString	modelType () const =0
virtual MlTaskType	taskType () const =0

Detailed Description

Backend-agnostic inference interface: load, predict, save plus model/task descriptors.

Definition at line 57 of file ml_model.h.

Inheritance diagram for MLLIB::MlModel:

Member Typedef Documentation

SPtr

typedef QSharedPointer<MlModel> MLLIB::MlModel::SPtr

Shared pointer type for MlModel.

Definition at line 60 of file ml_model.h.

Constructor & Destructor Documentation

~MlModel()

virtual MLLIB::MlModel::~MlModel ( )

virtualdefault

Virtual destructor.

Member Function Documentation

load()

virtual bool MLLIB::MlModel::load ( const QString & path )

pure virtual

Load a model from disk.

Parameters

[in]

path

File path.

Returns

True if successful.

Implemented in MLLIB::MlOnnxModel.

modelType()

virtual QString MLLIB::MlModel::modelType ( ) const

pure virtual

Returns

Human-readable model type name.

Implemented in MLLIB::MlOnnxModel.

predict()

virtual MlTensor MLLIB::MlModel::predict ( const MlTensor & input ) const

pure virtual

Run inference on the given input tensor.

Parameters

[in]

input

The input data.

Returns

The prediction result.

Implemented in MLLIB::MlOnnxModel.

save()

virtual bool MLLIB::MlModel::save ( const QString & path ) const

pure virtual

Serialise the model to disk.

Parameters

[in]

path

File path.

Returns

True if successful.

Implemented in MLLIB::MlOnnxModel.

taskType()

virtual MlTaskType MLLIB::MlModel::taskType ( ) const

pure virtual

Returns

The task type this model is configured for.

Implemented in MLLIB::MlOnnxModel.

---

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

• src/libraries/ml/ml_model.h