Image classifier base class. More...

#include <classifier.h>

Inheritance diagram for Beatmup::NNets::Classifier:

Public Member Functions
	Classifier (Context &context, ChunkCollection &data)
	Creates a Classifier instance. More...

	~Classifier ()

const std::vector< float > &	operator() (AbstractBitmap &input)
	Classifies an image (blocking). More...

Job	start (AbstractBitmap &input)
	Initiates the classification of a given image. More...

const std::vector< float > &	getProbabilities () const
	Returns the last classification results. More...

Public Member Functions inherited from Beatmup::NNets::Model
	Model (Context &context, std::initializer_list< AbstractOperation * > ops)
	Instantiates a model from a list of operations interconnecting them in a feedforward fashion. More...

	Model (Context &context)
	Instantiates an empty model. More...

	~Model ()

void	append (AbstractOperation *newOp, bool connect=false)
	Adds a new operation to the model. More...

void	append (std::initializer_list< AbstractOperation * > newOps, bool connect=false)
	Adds new operations to the model. More...

void	addOperation (const std::string &opName, AbstractOperation *newOp)
	Adds a new operation to the model before another operation in the execution order. More...

void	addOperation (const AbstractOperation &operation, AbstractOperation *newOp)

void	addConnection (const std::string &sourceOpName, const std::string &destOpName, int output=0, int input=0, int shuffle=0)
	Adds a connection between two given ops. More...

void	addOutput (const std::string &operation, int output=0)
	Enables reading output data from the model memory through getOutputData(). More...

void	addOutput (const AbstractOperation &operation, int output=0)

const float *	getOutputData (size_t &numSamples, const std::string &operation, int output=0) const
	Reads data from the model memory. More...

const float *	getOutputData (size_t &numSamples, const AbstractOperation &operation, int output=0) const

virtual void	prepare (GraphicPipeline &gpu, ChunkCollection &data)
	Prepares all operations: reads the model data from chunks and builds GPU programs. More...

bool	isReady () const

void	execute (TaskThread &thread, GraphicPipeline *gpu)
	Runs the inference. More...

bool	isOperationInModel (const AbstractOperation &operation) const
	Checks if a specific operation makes part of the model. More...

AbstractOperation &	getFirstOperation ()

AbstractOperation &	getLastOperation ()

const AbstractOperation &	getFirstOperation () const

const AbstractOperation &	getLastOperation () const

size_t	getNumberOfOperations () const

template<class OperationClass = AbstractOperation>
OperationClass &	getOperation (const std::string &operationName)
	Retrieves an operation by its name. More...

const ProgressTracking &	getPreparingProgress () const
	Returns model preparation progress tracking. More...

const ProgressTracking &	getInferenceProgress () const
	Returns inference progress tracking. More...

unsigned long	countMultiplyAdds () const
	Provides an estimation of the number of multiply-adds characterizing the model complexity. More...

unsigned long	countTexelFetches () const
	Provides an estimation of the total number of texels fetched by all the operations in the model per image. More...

size_t	getMemorySize () const
	Returns the amount of texture memory in bytes currently allocated by the model to run the inference. More...

Listing	serialize () const
	Returns serialized representation of the model as a Listing. More...

std::string	serializeToString () const
	Returns serialized representation of the model as a string. More...

void	setProfiler (Profiler *profiler)
	Attaches a profiler instance to meter the execution time per operation during the inference. More...

Public Member Functions inherited from Beatmup::GL::ProgramBank
	ProgramBank (Context &context)

	~ProgramBank ()

GL::RenderingProgram *	operator() (GraphicPipeline &gpu, const std::string &code, bool enableExternalTextures=false)
	Provides a program given a fragment shader source code. More...

void	release (GraphicPipeline &gpu, GL::RenderingProgram *program)
	Marks a program as unused any more. More...

Public Member Functions inherited from Beatmup::Object
virtual	~Object ()

Public Member Functions inherited from Beatmup::NNets::InferenceTask
	InferenceTask (Model &model, ChunkCollection &data)

void	connect (AbstractBitmap &image, AbstractOperation &operation, int inputIndex=0)
	Connects an image to a specific operation input. More...

void	connect (AbstractBitmap &image, const std::string &operation, int inputIndex=0)

Protected Attributes
Context &	context

Protected Attributes inherited from Beatmup::NNets::Model
std::vector< AbstractOperation * >	ops
	model operations More...

ProgressTracking	preparingProgress
	model preparation progress More...

ProgressTracking	inferenceProgress
	inference progress More...

bool	ready
	if `true`, ops are connected to each other and storages are allocated More...

Protected Attributes inherited from Beatmup::GL::ProgramBank
Context &	context

Protected Attributes inherited from Beatmup::NNets::InferenceTask
ChunkCollection &	data

Model &	model

Additional Inherited Members
Public Types inherited from Beatmup::AbstractTask
enum class	TaskDeviceRequirement { CPU_ONLY , GPU_OR_CPU , GPU_ONLY }
	Specifies which device (CPU and/or GPU) is used to run the task. More...

Static Public Member Functions inherited from Beatmup::AbstractTask
static ThreadIndex	validThreadCount (int number)
	Valid thread count from a given integer value. More...

Protected Member Functions inherited from Beatmup::NNets::Model
void	freeMemory ()
	Frees all allocated storages. More...

Storage &	allocateStorage (GraphicPipeline &gpu, const Size size, bool forGpu=true, bool forCpu=false, const int pad=0, const int reservedChannels=0)
	Allocates a new storage. More...

Storage &	allocateFlatStorage (GraphicPipeline &gpu, const int size)
	Allocates a new flat storage. More...

GL::Vector &	allocateVector (GraphicPipeline &gpu, const int size)
	Allocates a vector that can be used as operation input or output. More...

InternalBitmap &	allocateTexture (GraphicPipeline &gpu, const Size size)
	Allocates a texture that can be used as operation input or output. More...

bool	isPreceding (const AbstractOperation &first, const AbstractOperation &second) const
	Checks whether an operation goes before another operation in the model according the ops execution order. More...

AbstractOperation *	operator[] (const std::string &operationName)

const AbstractOperation *	operator[] (const std::string &operationName) const

void	addConnection (AbstractOperation &source, AbstractOperation &dest, int output=0, int input=0, int shuffle=0)

Detailed Description

Image classifier base class.

Combines a runnable InferenceTask with a Model assuming Conv2D and Softmax are its first and last operations respectively.

Definition at line 35 of file classifier.h.

Constructor & Destructor Documentation

◆ Classifier()

Classifier::Classifier	(	Context &	context,
		ChunkCollection &	data
	)

Creates a Classifier instance.

Parameters

context	A context instance Classifier will use to store its internal data
data	A ChunkCollection to access to the classifier model data

Definition at line 29 of file classifier.cpp.

                                                              :
     Model(context),
     InferenceTask(*this, data),
     context(context)
 {}

◆ ~Classifier()

Classifier::~Classifier ( )

Definition at line 36 of file classifier.cpp.

                         {
     for (auto op : ops)
         delete op;
     ops.clear();
 }

Member Function Documentation

◆ operator()()

const std::vector< float > & Classifier::operator() ( AbstractBitmap & input )

Classifies an image (blocking).

The very first call includes the model preparation and might be slow as hell. Subsequent calls only run the inference and are likely much faster.

Parameters

[in] input The input image

Returns: a vector of probabilities per class.

Definition at line 43 of file classifier.cpp.

                                                                     {
     connect(input, *ops[0], 0);
     context.performTask(*this);
     return getProbabilities();
 }

◆ start()

Job Classifier::start ( AbstractBitmap & input )

Initiates the classification of a given image.

The call is non-blocking.

Parameters

[in] input The input image

Returns: a job corresponding to the submitted task.

Definition at line 50 of file classifier.cpp.

                                            {
     connect(input, *ops[0], 0);
     return context.submitTask(*this);
 }

◆ getProbabilities()

const std::vector<float>& Beatmup::NNets::Classifier::getProbabilities ( ) const

inline

Returns the last classification results.

Returns: a vector of probabilities per class.

Definition at line 69 of file classifier.h.

                                                                     {
                 return static_cast<const Softmax&>(getLastOperation()).getProbabilities();
             }

Member Data Documentation

◆ context

Context& Beatmup::NNets::Classifier::context

protected

Definition at line 37 of file classifier.h.

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

core/nnets/classifier.h
core/nnets/classifier.cpp

Public Member Functions

Protected Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ Classifier()

◆ ~Classifier()

Member Function Documentation

◆ operator()()

◆ start()

◆ getProbabilities()

Member Data Documentation

◆ context