eVision.EasyDeepLearning.EClassifier allows to train a classifier using an eVision.EasyDeepLearning.EDataset object and classify new images. More...

Inheritance diagram for eVision.EasyDeepLearning.EClassifier:

[legend]

Collaboration diagram for eVision.EasyDeepLearning.EClassifier:

[legend]

Public Member Functions
None	__init__ (self)
	Constructs a eVision.EasyDeepLearning.EClassifier object.
None	__init__ (self, eVision.EasyDeepLearning.EClassifier other)
	Copy constructor of a eVision.EasyDeepLearning.EClassifier object.
None	SerializeSettings (self, eVision.ESerializer\|None serializer)
	Serializes the classifier settings.
None	LoadAsPretrained (self, str path)
	Loads the classifier and use it as a pre-trained model.
None	LoadOnnxModelAsPretrained (self, str path)
	Loads the ONNX model as a pre-trained model.
None	LoadOnnxModel (self, str path)
	Loads the ONNX model for inference.
bool	HasPretrainedModel (self)
	Whether a pre-trained model for the current configuration can be found.
eVision.EasyDeepLearning.EClassificationMetrics	GetTrainingMetrics (self, int id)
	Gets the metrics obtained with the training dataset at the given iteration.
eVision.EasyDeepLearning.EClassificationMetrics	GetValidationMetrics (self, int id)
	Gets the metrics obtained with the validation dataset at the given iteration.
None	Train (self, eVision.EasyDeepLearning.EDataset dataset)
	Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.
None	Train (self, eVision.EasyDeepLearning.EDataset dataset, eVision.EasyDeepLearning.EDataAugmentation dataAugmentation)
	Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.
None	Train (self, eVision.EasyDeepLearning.EDataset trainingDataset, eVision.EasyDeepLearning.EDataset validationDataset)
	Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.
None	Train (self, eVision.EasyDeepLearning.EDataset trainingDataset, eVision.EasyDeepLearning.EDataset validationDataset, eVision.EasyDeepLearning.EDataAugmentation dataAugmentation)
	Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.
None	Train (self, eVision.EasyDeepLearning.EDataset dataset, int iterations)
	Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.
None	Train (self, eVision.EasyDeepLearning.EDataset dataset, eVision.EasyDeepLearning.EDataAugmentation dataAugmentation, int iterations)
	Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.
None	Train (self, eVision.EasyDeepLearning.EDataset trainingDataset, eVision.EasyDeepLearning.EDataset validationDataset, int iterations)
	Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.
None	Train (self, eVision.EasyDeepLearning.EDataset trainingDataset, eVision.EasyDeepLearning.EDataset validationDataset, eVision.EasyDeepLearning.EDataAugmentation dataAugmentation, int iterations)
	Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.
eVision.EasyDeepLearning.EClassificationResult	Classify (self, eVision.EBaseROI img)
	Classifies images and returns the complete results as an eVision.EasyDeepLearning.EClassificationResult object.
eVision.EasyDeepLearning.EClassificationResult	Classify (self, eVision.EBaseROI img, eVision.ERegion mask)
	Classifies images and returns the complete results as an eVision.EasyDeepLearning.EClassificationResult object.
list[eVision._eVision.EasyDeepLearning.EClassificationResult]	Classify (self, list[eVision._eVision.EBaseROI\|None] imgList, eVision.ERegion mask)
	Classifies images and returns the complete results as an eVision.EasyDeepLearning.EClassificationResult object.
list[eVision._eVision.EasyDeepLearning.EClassificationResult]	Classify (self, list[eVision._eVision.EBaseROI\|None] imgList)
	Classifies images and returns the complete results as an eVision.EasyDeepLearning.EClassificationResult object.
eVision.EasyDeepLearning.EClassificationResult	Classify (self, eVision.EBaseROI img, eVision.ERegion mask, eVision.EFrame frame)
	Classifies images and returns the complete results as an eVision.EasyDeepLearning.EClassificationResult object.
list[eVision._eVision.EasyDeepLearning.EClassificationResult]	Classify (self, list[eVision._eVision.EBaseROI\|None] imgList, eVision.ERegion mask, eVision.EFrame frame)
	Classifies images and returns the complete results as an eVision.EasyDeepLearning.EClassificationResult object.
eVision.EasyDeepLearning.EClassificationMetrics	Evaluate (self, eVision.EasyDeepLearning.EDataset dataset)
	Evaluates the eVision.EasyDeepLearning.EClassifier using the given eVision.EasyDeepLearning.EDataset.
eVision.EImageBW8	GetHeatMap (self, eVision.EBaseROI image, str label)
	Gets a heatmap associated with the given label.
eVision.EImageC24	GetColorizedHeatMap (self, eVision.EBaseROI image, str label)
	Gets a colorized heatmap associated with the given label.
eVision.EImageC24A	GetColorizedHeatmapWithTransparency (self, eVision.EBaseROI image, str label, float minAlpha, float maxAlpha, eVision.EasyDeepLearning.EHeatmapColormap colormap)
	Colorized heatmap with transparency.
eVision.EImageC24A	GetColorizedHeatmapWithTransparency (self, eVision.EBaseROI image, str label, float minAlpha, float maxAlpha)
	Colorized heatmap with transparency.
None	LearnOODParameters (self, eVision.EasyDeepLearning.EDataset trainList, eVision.EasyDeepLearning.EDataset valList)
	Learns OOD parameters using training data.
None	LearnOODParameters (self, list[eVision._eVision.EBaseROI\|None] trainList, list[eVision._eVision.EBaseROI\|None] valList)
	Learns OOD parameters using training data.
bool	HasOODParameters (self)
	Checks whether the OOD parameters have been learned.
Public Member Functions inherited from eVision.EasyDeepLearning.EDeepLearningTool
None	Load (self, str filePath)
	Loads a deep learning tool.
None	Load (self, eVision.ESerializer\|None serializer)
	Loads a deep learning tool.
eVision.EasyDeepLearning.EDeepLearningTool\|None	Clone (self)
	Clones this tool.
None	Save (self, str filePath, bool includeTrainingModel)
	Saves the settings, inference and training model of the deep learning tool.
None	Save (self, str filePath)
	Saves the settings, inference and training model of the deep learning tool.
None	Save (self, eVision.ESerializer\|None serializer, bool includeTrainingModel)
	Saves the settings, inference and training model of the deep learning tool.
None	Save (self, eVision.ESerializer\|None serializer)
	Saves the settings, inference and training model of the deep learning tool.
None	SerializeInferenceModel (self, eVision.ESerializer\|None serializer)
	Serializes the inference model of the tool.
None	SerializeTrainingModel (self, eVision.ESerializer\|None serializer)
	Serializes the training model of the tool.
None	SaveSettings (self, str filePath)
	Saves the settings of the tool to a file.
None	SaveInferenceModel (self, str filePath)
	Saves the tool's inference model to a file.
None	SaveTrainingModel (self, str filePath)
	Saves the tool's training model to a file.
None	LoadSettings (self, str filePath)
	Loads the settings of a tool.
None	LoadInferenceModel (self, str filePath)
	Loads the tool's inference model.
None	LoadTrainingModel (self, str filePath)
	Loads the tool's training model.
None	UnloadInferenceModel (self)
	Unloads the inference model.
None	UnloadTrainingModel (self)
	Unloads the training model.
None	UnloadModels (self)
	Unloads the inference and training model.
bool	HasInferenceModel (self)
	Whether the inference model is loaded or created when the tool is not yet trained.
bool	HasTrainingModel (self)
	Whether the training model is loaded or created when the tool is not yet trained.
bool	IsTrained (self)
	Tells whether the deep learning tool has been trained.
str	GetAvailableDeviceName (self, int i)
	Name of the i-th device of the current engine.
eVision.EasyDeepLearning.EDeepLearningDevice	GetAvailableDevice (self, int i)
	i-th eVision.EasyDeepLearning.EDeepLearningDevice of the current engine.
None	SetActiveDevice (self, eVision.EasyDeepLearning.EDeepLearningDevice device)
	Sets the device with which to run or train the model.
eVision.EasyDeepLearning.EDeepLearningDevice	GetActiveDevice (self, int i)
	Gets the active device.
eVision.EasyDeepLearning.EDeepLearningDevice	GetActiveDevice (self)
	Gets the active device.
bool	HasEngineSetupData (self)
	Whether the inference model has engine setup data.
None	ClearEngineSetupData (self)
	Clears the engine data saved in the inference model.
bool	IsTraining (self)
	Indicates whether the object is currently training.
int	WaitForTrainingCompletion (self, int timeout)
	Waits until the training is complete or the timeout is expired.
int	WaitForTrainingCompletion (self)
	Waits until the training is complete or the timeout is expired.
int	WaitForIterationCompletion (self)
	Waits until an iteration is complete.
int	StopTraining (self, bool wait)
	Stops training and returns the last completed iteration.
None	SetLearningRate (self, eVision.EasyDeepLearning.EDeepLearningLearningRateType type, list[float] parameters)
	Specifies how the value of the learning rate and how it evolves during training.
None	InitializeInference (self, int width, int height, eVision.EImageType imageType, int numImages)
	Initializes the neural network for inference (i.e.
None	InitializeInference (self, eVision.EBaseROI img)
	Initializes the neural network for inference (i.e.
None	InitializeInference (self, list[eVision._eVision.EBaseROI\|None] imgList)
	Initializes the neural network for inference (i.e.
str	GetLabel (self, int index)
	Gets the label from its index.
None	SetLabel (self, int index, str label)
	Changes a label predicted by the tool.
None	SetLabelWeight (self, int index, float weight)
	Sets the label weight.
float	GetLabelWeight (self, int index)
	Gets the label weight.
None	SetLabelColor (self, int index, eVision.ERGBColor c)
	Changes a label color.
eVision.ERGBColor	GetLabelColor (self, int index)
	Label color.
None	SetLabelOpacity (self, int index, int opacity)
	Changes a label opacity (between 0 for fully transparent and 255 for opaque color).
int	GetLabelOpacity (self, int index)
	Gets the label opacity (between 0 for fully transparent and 255 for opaque color).
int	GetOptimalNumImagesForBatchSize (self, eVision.EBaseROI sampleImage)
	Optimal number of images to process together for inference given the batch size and eVision.EasyDeepLearning.EDeepLearningTool.GetNumPatchesForImage.
int	GetOptimalNumImagesForBatchSize (self, int imageWidth, int imageHeight)
	Optimal number of images to process together for inference given the batch size and eVision.EasyDeepLearning.EDeepLearningTool.GetNumPatchesForImage.
int	GetNumPatchesForImage (self, eVision.EBaseROI sampleImage)
	Number of patches that will be extracted from an input image to perform inference.
int	GetNumPatchesForImage (self, int imageWidth, int imageHeight)
	Number of patches that will be extracted from an input image to perform inference.
None	Clean (self)
	Reset the engine and clean CPU and GPU memory allocated for running the model.

Static Public Member Functions
str	GetAvailableModelTypes (int i)
	Get the i-th available models to be used with eVision.EasyDeepLearning.EClassifier.ModelType.
int	GetNumAvailableModelTypes ()
	Number of available models for training an EasyClassify tool.
Static Public Member Functions inherited from eVision.EasyDeepLearning.EDeepLearningTool
eVision.EasyDeepLearning.EDeepLearningTool\|None	Create (str path)
	Factory method to open a deep learning tool.
eVision.EasyDeepLearning.EDeepLearningTool\|None	Create (eVision.ESerializer\|None serializer)
	Factory method to open a deep learning tool.
eVision.EasyDeepLearning.EDeepLearningTool\|None	Create (eVision.EasyDeepLearning.EDeepLearningToolType type)
	Factory method to open a deep learning tool.
int	GetNumAvailableEngines ()
	Number of available engines.
str	GetAvailableEngineName (int id)
	Gets the name of the engine given its id.
list[str]	GetAvailableEngines ()
	Available engines.
list[eVision._eVision.EasyDeepLearning.EDeepLearningDevice]	GetAvailableDevicesForEngine (str engine)
	Available devices for the specified engine.

Protected Member Functions
eVision.EasyDeepLearning.EDeepLearningToolType	_ToolType__getter (self)
	\cond
bool	_UsePretrainedModel__getter (self)
	\cond
	_UsePretrainedModel__setter (self, bool value)
	Whether to use a pre-trained model when training.
int	_Width__getter (self)
	\cond
	_Width__setter (self, int value)
	Width for input images of the classifier.
int	_Height__getter (self)
	\cond
	_Height__setter (self, int value)
	Height for input images of the classifier.
int	_Channels__getter (self)
	\cond
	_Channels__setter (self, int value)
	Number of channels for input images of the classifier.
bool	_EnableAutomaticImageReformat__getter (self)
	\cond
	_EnableAutomaticImageReformat__setter (self, bool value)
	Enable automatic image reformat (true by default).
bool	_EnableHistogramEqualization__getter (self)
	\cond
	_EnableHistogramEqualization__setter (self, bool value)
	Enable histogram equalization of all images passing through the classifier.
int	_MinimumWidth__getter (self)
	\cond
int	_MinimumHeight__getter (self)
	\cond
eVision.EasyDeepLearning.EClassifierCapacity	_Capacity__getter (self)
	\cond
	_Capacity__setter (self, eVision.EasyDeepLearning.EClassifierCapacity value)
	Capacity of classifier to use.
str	_ModelType__getter (self)
	\cond
	_ModelType__setter (self, str value)
	Model type for training.
float	_OODThreshold__getter (self)
	\cond
	_OODThreshold__setter (self, float value)
	Out-Of-Distribution (OOD) threshold below which an image is considered to be OOD.
bool	_ComputeHeatmapWithResult__getter (self)
	\cond
	_ComputeHeatmapWithResult__setter (self, bool value)
	Whether to always compute the heatmap along the result when applying the tool.
bool	_ComputeOODWithResult__getter (self)
	\cond
	_ComputeOODWithResult__setter (self, bool value)
	Whether to compute the OOD parameters while training.
Protected Member Functions inherited from eVision.EasyDeepLearning.EDeepLearningTool
bool	_EnableGPU__getter (self)
	\cond
	_EnableGPU__setter (self, bool value)
	Enable the use of a GPU for training and inference of the deep learning tool.
list[int]	_GPUIndexes__getter (self)
	\cond
	_GPUIndexes__setter (self, list[int] value)
	Indexes of the GPUs to use for computations.
int	_NumGPUs__getter (self)
	\cond
str	_Engine__getter (self)
	\cond
	_Engine__setter (self, str value)
	Sets the engine with which to execute or train the neural network.
eVision.EasyDeepLearning.EDeepLearningInferencePrecision	_InferencePrecision__getter (self)
	\cond
	_InferencePrecision__setter (self, eVision.EasyDeepLearning.EDeepLearningInferencePrecision value)
	Inference precision.
int	_NumAvailableDevices__getter (self)
	\cond
list[eVision._eVision.EasyDeepLearning.EDeepLearningDevice]	_AvailableDevices__getter (self)
	\cond
int	_NumActiveDevices__getter (self)
	\cond
	_ActiveDeviceByName__setter (self, str value)
	\cond
	_ActiveDeviceById__setter (self, int value)
	\cond
list[eVision._eVision.EasyDeepLearning.EDeepLearningDevice]	_ActiveDevices__getter (self)
	\cond
	_ActiveDevices__setter (self, list[eVision._eVision.EasyDeepLearning.EDeepLearningDevice] value)
	Devices with which to run or train the model.
	_ActiveDevicesById__setter (self, list[int] value)
	\cond
eVision.EasyDeepLearning.EDeepLearningExecutionSettings	_ExecutionSettings__getter (self)
	\cond
	_ExecutionSettings__setter (self, eVision.EasyDeepLearning.EDeepLearningExecutionSettings value)
	Execution settings of the tool (engine, device(s), inference precision, batch size settings).
eVision.EasyDeepLearning.EDeepLearningDevice	_EngineSetupDataDevice__getter (self)
	\cond
eVision.EasyDeepLearning.EDeepLearningInferencePrecision	_EngineSetupDataInferencePrecision__getter (self)
	\cond
int	_EngineSetupDataBatchSize__getter (self)
	\cond
bool	_OptimizeBatchSize__getter (self)
	\cond
	_OptimizeBatchSize__setter (self, bool value)
	Indicates whether to optimize the batch size (see eVision.EasyDeepLearning.EDeepLearningTool.BatchSize) to maximize the training and inference speed according to the engine, the device and the available memory.
int	_BatchSizeForMaximumInferenceSpeed__getter (self)
	\cond
int	_BatchSize__getter (self)
	\cond
	_BatchSize__setter (self, int value)
	Batch size.
float	_CurrentTrainingProgression__getter (self)
	\cond
int	_CurrentTrainingFinishedIterations__getter (self)
	\cond
int	_CurrentTrainingNumIterations__getter (self)
	\cond
int	_NumTrainedIterations__getter (self)
	\cond
int	_BestIteration__getter (self)
	\cond
int	_ImageCacheSize__getter (self)
	\cond
	_ImageCacheSize__setter (self, int value)
	Size in byte of the image cache.
str	_Path__getter (self)
	\cond
str	_InferenceModelPath__getter (self)
	\cond
str	_TrainingModelPath__getter (self)
	\cond
str	_SettingsPath__getter (self)
	\cond
int	_AutoSavePeriod__getter (self)
	\cond
	_AutoSavePeriod__setter (self, int value)
	Auto-save period.
eVision.EasyDeepLearning.EDeepLearningLearningRateType	_LearningRateType__getter (self)
	\cond
list[float]	_LearningRateParameters__getter (self)
	\cond
bool	_EnableDeterministicTraining__getter (self)
	\cond
	_EnableDeterministicTraining__setter (self, bool value)
	Whether to use deterministic training algorithm that allows to repeatable training results.
int	_DeterministicTrainingRandomSeed__getter (self)
	\cond
	_DeterministicTrainingRandomSeed__setter (self, int value)
	Random seed to use when eVision.EasyDeepLearning.EDeepLearningTool.EnableDeterministicTraining is set to true.
int	_NumLabels__getter (self)
	\cond

Properties
	ToolType = property(_ToolType__getter, None)
	\endcond
	UsePretrainedModel = property(_UsePretrainedModel__getter, _UsePretrainedModel__setter)
	\endcond
	Width = property(_Width__getter, _Width__setter)
	\endcond
	Height = property(_Height__getter, _Height__setter)
	\endcond
	Channels = property(_Channels__getter, _Channels__setter)
	\endcond
	EnableAutomaticImageReformat = property(_EnableAutomaticImageReformat__getter, _EnableAutomaticImageReformat__setter)
	\endcond
	EnableHistogramEqualization = property(_EnableHistogramEqualization__getter, _EnableHistogramEqualization__setter)
	\endcond
	MinimumWidth = property(_MinimumWidth__getter, None)
	\endcond
	MinimumHeight = property(_MinimumHeight__getter, None)
	\endcond
	Capacity = property(_Capacity__getter, _Capacity__setter)
	\endcond
	ModelType = property(_ModelType__getter, _ModelType__setter)
	\endcond
	OODThreshold = property(_OODThreshold__getter, _OODThreshold__setter)
	\endcond
	ComputeHeatmapWithResult = property(_ComputeHeatmapWithResult__getter, _ComputeHeatmapWithResult__setter)
	\endcond
	ComputeOODWithResult = property(_ComputeOODWithResult__getter, _ComputeOODWithResult__setter)
	\endcond
Properties inherited from eVision.EasyDeepLearning.EDeepLearningTool
	ToolType = property(_ToolType__getter, None)
	\endcond
	EnableGPU = property(_EnableGPU__getter, _EnableGPU__setter)
	\endcond
	GPUIndexes = property(_GPUIndexes__getter, _GPUIndexes__setter)
	\endcond
	NumGPUs = property(_NumGPUs__getter, None)
	\endcond
	Engine = property(_Engine__getter, _Engine__setter)
	\endcond
	InferencePrecision = property(_InferencePrecision__getter, _InferencePrecision__setter)
	\endcond
	NumAvailableDevices = property(_NumAvailableDevices__getter, None)
	\endcond
	AvailableDevices = property(_AvailableDevices__getter, None)
	\endcond
	NumActiveDevices = property(_NumActiveDevices__getter, None)
	\endcond
	ActiveDeviceByName = property(None, _ActiveDeviceByName__setter)
	\endcond
	ActiveDeviceById = property(None, _ActiveDeviceById__setter)
	\endcond
	ActiveDevices = property(_ActiveDevices__getter, _ActiveDevices__setter)
	\endcond
	ActiveDevicesById = property(None, _ActiveDevicesById__setter)
	\endcond
	ExecutionSettings = property(_ExecutionSettings__getter, _ExecutionSettings__setter)
	\endcond
	EngineSetupDataDevice = property(_EngineSetupDataDevice__getter, None)
	\endcond
	EngineSetupDataInferencePrecision = property(_EngineSetupDataInferencePrecision__getter, None)
	\endcond
	EngineSetupDataBatchSize = property(_EngineSetupDataBatchSize__getter, None)
	\endcond
	OptimizeBatchSize = property(_OptimizeBatchSize__getter, _OptimizeBatchSize__setter)
	\endcond
	BatchSizeForMaximumInferenceSpeed = property(_BatchSizeForMaximumInferenceSpeed__getter, None)
	\endcond
	BatchSize = property(_BatchSize__getter, _BatchSize__setter)
	\endcond
	CurrentTrainingProgression = property(_CurrentTrainingProgression__getter, None)
	\endcond
	CurrentTrainingFinishedIterations = property(_CurrentTrainingFinishedIterations__getter, None)
	\endcond
	CurrentTrainingNumIterations = property(_CurrentTrainingNumIterations__getter, None)
	\endcond
	NumTrainedIterations = property(_NumTrainedIterations__getter, None)
	\endcond
	BestIteration = property(_BestIteration__getter, None)
	\endcond
	ImageCacheSize = property(_ImageCacheSize__getter, _ImageCacheSize__setter)
	\endcond
	Path = property(_Path__getter, None)
	\endcond
	InferenceModelPath = property(_InferenceModelPath__getter, None)
	\endcond
	TrainingModelPath = property(_TrainingModelPath__getter, None)
	\endcond
	SettingsPath = property(_SettingsPath__getter, None)
	\endcond
	AutoSavePeriod = property(_AutoSavePeriod__getter, _AutoSavePeriod__setter)
	\endcond
	LearningRateType = property(_LearningRateType__getter, None)
	\endcond
	LearningRateParameters = property(_LearningRateParameters__getter, None)
	\endcond
	EnableDeterministicTraining = property(_EnableDeterministicTraining__getter, _EnableDeterministicTraining__setter)
	\endcond
	DeterministicTrainingRandomSeed = property(_DeterministicTrainingRandomSeed__getter, _DeterministicTrainingRandomSeed__setter)
	\endcond
	NumLabels = property(_NumLabels__getter, None)
	\endcond

Detailed Description

eVision.EasyDeepLearning.EClassifier allows to train a classifier using an eVision.EasyDeepLearning.EDataset object and classify new images.

As required by Deep Learning techniques, the input image of eVision.EasyDeepLearning.EClassifier must be of the same format (width, height, number of channels). By default, this format will be 224x224xC (which is the format used for pre-training our networks) with C being the number of channel of the first image of the dataset. The format can also be specified by the eVision.EasyDeepLearning.EClassifier.Width, eVision.EasyDeepLearning.EClassifier.Height and eVision.EasyDeepLearning.EClassifier.Channels unless its width and height is smaller than the minimum width and height supported by the classifier. In this case, the input resolution will be the minimum resolution supported by the classifier. (See eVision.EasyDeepLearning.EClassifier.MinimumWidth and eVision.EasyDeepLearning.EClassifier.MinimumHeight). methods.

By default, images that don't satisfy the image format of the classifier are automatically reformatted. This behavior can be controlled through the eVision.EasyDeepLearning.EClassifier.EnableAutomaticImageReformat method. When the automatic image reformatting is disabled, training or classifying an image that doesn't satisfy the input image format will result in an exception.

Once trained, the input image format cannot be changed.

Remarks:

License(s): EasyClassify or EasyClassifyInference

Constructor & Destructor Documentation

◆ init() [1/2]

None eVision.EasyDeepLearning.EClassifier.__init__ ( self )

Constructs a eVision.EasyDeepLearning.EClassifier object.

◆ init() [2/2]

None eVision.EasyDeepLearning.EClassifier.__init__	(		self,
		eVision.EasyDeepLearning.EClassifier	other )

Copy constructor of a eVision.EasyDeepLearning.EClassifier object.

Parameters

other Reference to the eVision.EasyDeepLearning.EClassifier object that should be copied

Member Function Documentation

◆ _Capacity__getter()

eVision.EasyDeepLearning.EClassifierCapacity eVision.EasyDeepLearning.EClassifier._Capacity__getter ( self )

protected

\cond

Capacity of classifier to use. Be aware that changing the classifier capacity will delete the effect of any previous training. The capacity will be translated to the corresponding type (Small, Normal, or Large).

Deprecated: Deprecated in version 22.12. Scheduled to be removed in version 27.6.

◆ _Capacity__setter()

eVision.EasyDeepLearning.EClassifier._Capacity__setter	(		self,
		eVision.EasyDeepLearning.EClassifierCapacity	value )

protected

Capacity of classifier to use.

Be aware that changing the classifier capacity will delete the effect of any previous training. The capacity will be translated to the corresponding type (Small, Normal, or Large).

Deprecated: Deprecated in version 22.12. Scheduled to be removed in version 27.6.

◆ _Channels__getter()

int eVision.EasyDeepLearning.EClassifier._Channels__getter ( self )

protected

\cond

Number of channels for input images of the classifier. The number of channels can be either 1 (monochrome image) or 3 (RGB image). By default, this value will be set from the format of the first image added to the training dataset.

Remarks:

If the classifier is not trained or the value was not explicitly set, its value will be 0.

◆ _Channels__setter()

eVision.EasyDeepLearning.EClassifier._Channels__setter	(		self,
		int	value )

protected

Number of channels for input images of the classifier.

The number of channels can be either 1 (monochrome image) or 3 (RGB image). By default, this value will be set from the format of the first image added to the training dataset.

Remarks:

If the classifier is not trained or the value was not explicitly set, its value will be 0.

◆ _ComputeHeatmapWithResult__getter()

bool eVision.EasyDeepLearning.EClassifier._ComputeHeatmapWithResult__getter ( self )

protected

\cond

Whether to always compute the heatmap along the result when applying the tool. If true, the heatmap is available through eVision.EasyDeepLearning.EClassificationResult.Heatmap.

◆ _ComputeHeatmapWithResult__setter()

eVision.EasyDeepLearning.EClassifier._ComputeHeatmapWithResult__setter	(		self,
		bool	value )

protected

Whether to always compute the heatmap along the result when applying the tool.

If true, the heatmap is available through eVision.EasyDeepLearning.EClassificationResult.Heatmap.

◆ _ComputeOODWithResult__getter()

bool eVision.EasyDeepLearning.EClassifier._ComputeOODWithResult__getter ( self )

protected

\cond

Whether to compute the OOD parameters while training. Also determines whether the OOD score is computed alongside the result when applying the tool. If true, the OOD score is available through eVision.EasyDeepLearning.EClassificationResult.OODScore.

◆ _ComputeOODWithResult__setter()

eVision.EasyDeepLearning.EClassifier._ComputeOODWithResult__setter	(		self,
		bool	value )

protected

Whether to compute the OOD parameters while training.

Also determines whether the OOD score is computed alongside the result when applying the tool. If true, the OOD score is available through eVision.EasyDeepLearning.EClassificationResult.OODScore.

◆ _EnableAutomaticImageReformat__getter()

bool eVision.EasyDeepLearning.EClassifier._EnableAutomaticImageReformat__getter ( self )

protected

\cond

Enable automatic image reformat (true by default).

◆ _EnableAutomaticImageReformat__setter()

eVision.EasyDeepLearning.EClassifier._EnableAutomaticImageReformat__setter	(		self,
		bool	value )

protected

Enable automatic image reformat (true by default).

◆ _EnableHistogramEqualization__getter()

bool eVision.EasyDeepLearning.EClassifier._EnableHistogramEqualization__getter ( self )

protected

\cond

Enable histogram equalization of all images passing through the classifier. (false by default)

◆ _EnableHistogramEqualization__setter()

eVision.EasyDeepLearning.EClassifier._EnableHistogramEqualization__setter	(		self,
		bool	value )

protected

Enable histogram equalization of all images passing through the classifier.

(false by default)

◆ _Height__getter()

int eVision.EasyDeepLearning.EClassifier._Height__getter ( self )

protected

\cond

Height for input images of the classifier. By default, this value will be set to 224 if it wasn't explicitly set before training.

Remarks:

If the classifier is not trained or the value was not explicitly set, its value will be 0.

◆ _Height__setter()

eVision.EasyDeepLearning.EClassifier._Height__setter	(		self,
		int	value )

protected

Height for input images of the classifier.

By default, this value will be set to 224 if it wasn't explicitly set before training.

Remarks:

If the classifier is not trained or the value was not explicitly set, its value will be 0.

◆ _MinimumHeight__getter()

int eVision.EasyDeepLearning.EClassifier._MinimumHeight__getter ( self )

protected

\cond

Minimum height for input images of the classifier. This value is equal to 1 for standard networks.

◆ _MinimumWidth__getter()

int eVision.EasyDeepLearning.EClassifier._MinimumWidth__getter ( self )

protected

\cond

Minimum width for input images of the classifier. This value is equal to 1 for standard networks.

◆ _ModelType__getter()

str eVision.EasyDeepLearning.EClassifier._ModelType__getter ( self )

protected

\cond

Model type for training. Default: "Normal".

The list of available models is available through eVision.EasyDeepLearning.EClassifier.GetAvailableModelTypes.

◆ _ModelType__setter()

eVision.EasyDeepLearning.EClassifier._ModelType__setter	(		self,
		str	value )

protected

Model type for training.

Default: "Normal".

The list of available models is available through eVision.EasyDeepLearning.EClassifier.GetAvailableModelTypes.

◆ _OODThreshold__getter()

float eVision.EasyDeepLearning.EClassifier._OODThreshold__getter ( self )

protected

\cond

Out-Of-Distribution (OOD) threshold below which an image is considered to be OOD.

Remarks:

If training has been carried out with eVision.EasyDeepLearning.EClassifier.ComputeOODWithResult set to True, the parameters have been automatically initialized. Otherwise, call eVision.EasyDeepLearning.EClassifier.LearnOODParameters with the training data before calling this method.

The OOD threshold is automatically initialized during learning. If needed, the parameter can also be changed manually.

◆ _OODThreshold__setter()

eVision.EasyDeepLearning.EClassifier._OODThreshold__setter	(		self,
		float	value )

protected

Out-Of-Distribution (OOD) threshold below which an image is considered to be OOD.

Remarks:

If training has been carried out with eVision.EasyDeepLearning.EClassifier.ComputeOODWithResult set to True, the parameters have been automatically initialized. Otherwise, call eVision.EasyDeepLearning.EClassifier.LearnOODParameters with the training data before calling this method.

The OOD threshold is automatically initialized during learning. If needed, the parameter can also be changed manually.

◆ _ToolType__getter()

eVision.EasyDeepLearning.EDeepLearningToolType eVision.EasyDeepLearning.EClassifier._ToolType__getter ( self )

protected

\cond

Type of the deep learning tool.

Reimplemented from eVision.EasyDeepLearning.EDeepLearningTool.

◆ _UsePretrainedModel__getter()

bool eVision.EasyDeepLearning.EClassifier._UsePretrainedModel__getter ( self )

protected

\cond

Whether to use a pre-trained model when training.

Default: true if the pre-trained model are found on the disk.

◆ _UsePretrainedModel__setter()

eVision.EasyDeepLearning.EClassifier._UsePretrainedModel__setter	(		self,
		bool	value )

protected

Whether to use a pre-trained model when training.

Default: true if the pre-trained model are found on the disk.

◆ _Width__getter()

int eVision.EasyDeepLearning.EClassifier._Width__getter ( self )

protected

\cond

Width for input images of the classifier. By default, this value will be set to 224 if it wasn't explicitly set before training.

Remarks:

If the classifier is not trained or the value was not explicitly set, its value will be 0.

◆ _Width__setter()

eVision.EasyDeepLearning.EClassifier._Width__setter	(		self,
		int	value )

protected

Width for input images of the classifier.

By default, this value will be set to 224 if it wasn't explicitly set before training.

Remarks:

If the classifier is not trained or the value was not explicitly set, its value will be 0.

◆ Classify() [1/6]

eVision.EasyDeepLearning.EClassificationResult eVision.EasyDeepLearning.EClassifier.Classify	(		self,
		eVision.EBaseROI	img )

Classifies images and returns the complete results as an eVision.EasyDeepLearning.EClassificationResult object.

The method throws an exception if the input image does not fulfill the input specification.

Remarks:

Classifying a set of images is usually faster than classifying each image sequentially.

To maximize the classification speed on a GPU, eVision.EasyDeepLearning.EDeepLearningTool.BatchSize and the size of the set of input images must be equal to the value returned by eVision.EasyDeepLearning.EDeepLearningTool.BatchSizeForMaximumInferenceSpeed.

Parameters

img	Image to classify

◆ Classify() [2/6]

eVision.EasyDeepLearning.EClassificationResult eVision.EasyDeepLearning.EClassifier.Classify	(		self,
		eVision.EBaseROI	img,
		eVision.ERegion	mask )

Classifies images and returns the complete results as an eVision.EasyDeepLearning.EClassificationResult object.

The method throws an exception if the input image does not fulfill the input specification.

Remarks:

Classifying a set of images is usually faster than classifying each image sequentially.

To maximize the classification speed on a GPU, eVision.EasyDeepLearning.EDeepLearningTool.BatchSize and the size of the set of input images must be equal to the value returned by eVision.EasyDeepLearning.EDeepLearningTool.BatchSizeForMaximumInferenceSpeed.

Parameters

img	Image to classify
mask	Mask of image to classify

◆ Classify() [3/6]

eVision.EasyDeepLearning.EClassificationResult eVision.EasyDeepLearning.EClassifier.Classify	(		self,
		eVision.EBaseROI	img,
		eVision.ERegion	mask,
		eVision.EFrame	frame )

Classifies images and returns the complete results as an eVision.EasyDeepLearning.EClassificationResult object.

The method throws an exception if the input image does not fulfill the input specification.

Remarks:

Classifying a set of images is usually faster than classifying each image sequentially.

To maximize the classification speed on a GPU, eVision.EasyDeepLearning.EDeepLearningTool.BatchSize and the size of the set of input images must be equal to the value returned by eVision.EasyDeepLearning.EDeepLearningTool.BatchSizeForMaximumInferenceSpeed.

Parameters

img	Image to classify
mask	Mask of image to classify
frame	Frame associated with the mask.

◆ Classify() [4/6]

list[eVision._eVision.EasyDeepLearning.EClassificationResult] eVision.EasyDeepLearning.EClassifier.Classify	(		self,
		list[eVision._eVision.EBaseROI \| None]	imgList )

Classifies images and returns the complete results as an eVision.EasyDeepLearning.EClassificationResult object.

The method throws an exception if the input image does not fulfill the input specification.

Remarks:

Classifying a set of images is usually faster than classifying each image sequentially.

To maximize the classification speed on a GPU, eVision.EasyDeepLearning.EDeepLearningTool.BatchSize and the size of the set of input images must be equal to the value returned by eVision.EasyDeepLearning.EDeepLearningTool.BatchSizeForMaximumInferenceSpeed.

Parameters

imgList Vector of images to classify

◆ Classify() [5/6]

list[eVision._eVision.EasyDeepLearning.EClassificationResult] eVision.EasyDeepLearning.EClassifier.Classify	(		self,
		list[eVision._eVision.EBaseROI \| None]	imgList,
		eVision.ERegion	mask )

Classifies images and returns the complete results as an eVision.EasyDeepLearning.EClassificationResult object.

The method throws an exception if the input image does not fulfill the input specification.

Remarks:

Classifying a set of images is usually faster than classifying each image sequentially.

To maximize the classification speed on a GPU, eVision.EasyDeepLearning.EDeepLearningTool.BatchSize and the size of the set of input images must be equal to the value returned by eVision.EasyDeepLearning.EDeepLearningTool.BatchSizeForMaximumInferenceSpeed.

Parameters

imgList	Vector of images to classify
mask	Mask of image to classify

◆ Classify() [6/6]

list[eVision._eVision.EasyDeepLearning.EClassificationResult] eVision.EasyDeepLearning.EClassifier.Classify	(		self,
		list[eVision._eVision.EBaseROI \| None]	imgList,
		eVision.ERegion	mask,
		eVision.EFrame	frame )

Classifies images and returns the complete results as an eVision.EasyDeepLearning.EClassificationResult object.

The method throws an exception if the input image does not fulfill the input specification.

Remarks:

Classifying a set of images is usually faster than classifying each image sequentially.

To maximize the classification speed on a GPU, eVision.EasyDeepLearning.EDeepLearningTool.BatchSize and the size of the set of input images must be equal to the value returned by eVision.EasyDeepLearning.EDeepLearningTool.BatchSizeForMaximumInferenceSpeed.

Parameters

imgList	Vector of images to classify
mask	Mask of image to classify
frame	Frame associated with the mask.

◆ Evaluate()

eVision.EasyDeepLearning.EClassificationMetrics eVision.EasyDeepLearning.EClassifier.Evaluate	(		self,
		eVision.EasyDeepLearning.EDataset	dataset )

Evaluates the eVision.EasyDeepLearning.EClassifier using the given eVision.EasyDeepLearning.EDataset.

Remarks:

This method computes various metrics (see eVision.EasyDeepLearning.EClassificationMetrics on the given dataset.

The method ignores the label weights and the data augmentation settings of the given dataset. However, the label weights can be taken into consideration in the returned eVision.EasyDeepLearning.EClassificationMetrics object.

License(s): EasyClassify

Parameters

dataset eVision.EasyDeepLearning.EDataset with which to evaluate the classifier

◆ GetAvailableModelTypes()

str eVision.EasyDeepLearning.EClassifier.GetAvailableModelTypes ( int i )

static

Get the i-th available models to be used with eVision.EasyDeepLearning.EClassifier.ModelType.

Parameters

i	Index of the model between 0 and eVision.EasyDeepLearning.EClassifier.GetNumAvailableModelTypes - 1.

◆ GetColorizedHeatMap()

eVision.EImageC24 eVision.EasyDeepLearning.EClassifier.GetColorizedHeatMap	(		self,
		eVision.EBaseROI	image,
		str	label )

Gets a colorized heatmap associated with the given label.

A heatmap is an image that indicates which pixels in the original image best explain the given label.

Parameters

image	A reference to the image we want to generate the heatmap from.
label	A reference to the string representing the label we want to explain for the given image.

◆ GetColorizedHeatmapWithTransparency() [1/2]

eVision.EImageC24A eVision.EasyDeepLearning.EClassifier.GetColorizedHeatmapWithTransparency	(		self,
		eVision.EBaseROI	image,
		str	label,
		float	minAlpha,
		float	maxAlpha )

Colorized heatmap with transparency.

When the minimum and maximum alpha values are different from each other, the transparency value for a pixel will depend on the value of the heatmap at that pixel. The range of heatmap values [0, 255] will be mapped to the range [minAlpha, maxAlpha].

Parameters

image	A reference to the image we want to generate the heatmap from.
label	A reference to the string representing the label we want to explain for the given image.
minAlpha	Minimum transparency value.
maxAlpha	Maximum transparency value.

◆ GetColorizedHeatmapWithTransparency() [2/2]

eVision.EImageC24A eVision.EasyDeepLearning.EClassifier.GetColorizedHeatmapWithTransparency	(		self,
		eVision.EBaseROI	image,
		str	label,
		float	minAlpha,
		float	maxAlpha,
		eVision.EasyDeepLearning.EHeatmapColormap	colormap )

Colorized heatmap with transparency.

When the minimum and maximum alpha values are different from each other, the transparency value for a pixel will depend on the value of the heatmap at that pixel. The range of heatmap values [0, 255] will be mapped to the range [minAlpha, maxAlpha].

Parameters

image	A reference to the image we want to generate the heatmap from.
label	A reference to the string representing the label we want to explain for the given image.
minAlpha	Minimum transparency value.
maxAlpha	Maximum transparency value.
colormap	Color map

◆ GetHeatMap()

eVision.EImageBW8 eVision.EasyDeepLearning.EClassifier.GetHeatMap	(		self,
		eVision.EBaseROI	image,
		str	label )

Gets a heatmap associated with the given label.

A heatmap is an image that indicates which pixels in the original image best explain the given label.

Parameters

image	A reference to the image we want to generate the heatmap from.
label	A reference to the string representing the label we want to explain for the given image.

◆ GetNumAvailableModelTypes()

int eVision.EasyDeepLearning.EClassifier.GetNumAvailableModelTypes ( )

static

Number of available models for training an EasyClassify tool.

◆ GetTrainingMetrics()

eVision.EasyDeepLearning.EClassificationMetrics eVision.EasyDeepLearning.EClassifier.GetTrainingMetrics	(		self,
		int	id )

Gets the metrics obtained with the training dataset at the given iteration.

The iterations are indexed between 0 and eVision.EasyDeepLearning.EDeepLearningTool.NumTrainedIterations - 1.

Parameters

id	The iteration index

◆ GetValidationMetrics()

eVision.EasyDeepLearning.EClassificationMetrics eVision.EasyDeepLearning.EClassifier.GetValidationMetrics	(		self,
		int	id )

Gets the metrics obtained with the validation dataset at the given iteration.

The iterations are indexed between 0 and eVision.EasyDeepLearning.EDeepLearningTool.NumTrainedIterations - 1.

Parameters

id	The iteration index

◆ HasOODParameters()

bool eVision.EasyDeepLearning.EClassifier.HasOODParameters ( self )

Checks whether the OOD parameters have been learned.

◆ HasPretrainedModel()

bool eVision.EasyDeepLearning.EClassifier.HasPretrainedModel ( self )

Whether a pre-trained model for the current configuration can be found.

◆ LearnOODParameters() [1/2]

None eVision.EasyDeepLearning.EClassifier.LearnOODParameters	(		self,
		eVision.EasyDeepLearning.EDataset	trainList,
		eVision.EasyDeepLearning.EDataset	valList )

Learns OOD parameters using training data.

The dataset must correspond to the dataset used to train the classifier.

Parameters

trainList	List of images used for training the EClassifier.
valList	List of images used as validation during the training of the EClassifier.

◆ LearnOODParameters() [2/2]

None eVision.EasyDeepLearning.EClassifier.LearnOODParameters	(		self,
		list[eVision._eVision.EBaseROI \| None]	trainList,
		list[eVision._eVision.EBaseROI \| None]	valList )

Learns OOD parameters using training data.

The dataset must correspond to the dataset used to train the classifier.

Parameters

trainList	List of images used for training the EClassifier.
valList	List of images used as validation during the training of the EClassifier.

◆ LoadAsPretrained()

None eVision.EasyDeepLearning.EClassifier.LoadAsPretrained	(		self,
		str	path )

Loads the classifier and use it as a pre-trained model.

Parameters

path	Path to the pre-trained model.

◆ LoadOnnxModel()

None eVision.EasyDeepLearning.EClassifier.LoadOnnxModel	(		self,
		str	path )

Loads the ONNX model for inference.

The methods will automatically create labels according to the number of classes in the ONNX model. The labels are named according to their position, i.e. "0", "1", etc. You can change the labels afterward using the method eVision.EasyDeepLearning.EDeepLearningTool.SetLabel.

◆ LoadOnnxModelAsPretrained()

None eVision.EasyDeepLearning.EClassifier.LoadOnnxModelAsPretrained	(		self,
		str	path )

Loads the ONNX model as a pre-trained model.

This method loads the architecture of the neural network as well as the trained weights in the model but discards the weights and parameters of some of the last layers to allow retraining on a new dataset with a different number of labels.

◆ SerializeSettings()

None eVision.EasyDeepLearning.EClassifier.SerializeSettings	(		self,
		eVision.ESerializer \| None	serializer )

Serializes the classifier settings.

Parameters

serializer Pointer to eVision.ESerializer

Reimplemented from eVision.EasyDeepLearning.EDeepLearningTool.

◆ Train() [1/8]

None eVision.EasyDeepLearning.EClassifier.Train	(		self,
		eVision.EasyDeepLearning.EDataset	dataset )

Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.

At the end of the training, the deep learning tool is in the state it was at the iteration that gave the minimum validation error. See eVision.EasyDeepLearning.EDeepLearningTool.BestIteration.

If no iterations is given, the training will stop automatically.

Remarks:

License(s): EasyClassify

Parameters

dataset eVision.EasyDeepLearning.EDataset with which to train and validate the deep learning tool

◆ Train() [2/8]

None eVision.EasyDeepLearning.EClassifier.Train	(		self,
		eVision.EasyDeepLearning.EDataset	dataset,
		eVision.EasyDeepLearning.EDataAugmentation	dataAugmentation )

Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.

At the end of the training, the deep learning tool is in the state it was at the iteration that gave the minimum validation error. See eVision.EasyDeepLearning.EDeepLearningTool.BestIteration.

If no iterations is given, the training will stop automatically.

Remarks:

License(s): EasyClassify

Parameters

dataset	eVision.EasyDeepLearning.EDataset with which to train and validate the deep learning tool
dataAugmentation	Data augmentation to use during training

◆ Train() [3/8]

None eVision.EasyDeepLearning.EClassifier.Train	(		self,
		eVision.EasyDeepLearning.EDataset	dataset,
		eVision.EasyDeepLearning.EDataAugmentation	dataAugmentation,
		int	iterations )

Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.

At the end of the training, the deep learning tool is in the state it was at the iteration that gave the minimum validation error. See eVision.EasyDeepLearning.EDeepLearningTool.BestIteration.

If no iterations is given, the training will stop automatically.

Remarks:

License(s): EasyClassify

Parameters

dataset	eVision.EasyDeepLearning.EDataset with which to train and validate the deep learning tool
dataAugmentation	Data augmentation to use during training
iterations	Number of iterations for training.

◆ Train() [4/8]

None eVision.EasyDeepLearning.EClassifier.Train	(		self,
		eVision.EasyDeepLearning.EDataset	dataset,
		int	iterations )

Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.

At the end of the training, the deep learning tool is in the state it was at the iteration that gave the minimum validation error. See eVision.EasyDeepLearning.EDeepLearningTool.BestIteration.

If no iterations is given, the training will stop automatically.

Remarks:

License(s): EasyClassify

Parameters

dataset	eVision.EasyDeepLearning.EDataset with which to train and validate the deep learning tool
iterations	Number of iterations for training.

◆ Train() [5/8]

None eVision.EasyDeepLearning.EClassifier.Train	(		self,
		eVision.EasyDeepLearning.EDataset	trainingDataset,
		eVision.EasyDeepLearning.EDataset	validationDataset )

Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.

At the end of the training, the deep learning tool is in the state it was at the iteration that gave the minimum validation error. See eVision.EasyDeepLearning.EDeepLearningTool.BestIteration.

If no iterations is given, the training will stop automatically.

Remarks:

License(s): EasyClassify

Parameters

trainingDataset	eVision.EasyDeepLearning.EDataset with which to train the deep learning tool
validationDataset	eVision.EasyDeepLearning.EDataset with which to validate the deep learning tool

◆ Train() [6/8]

None eVision.EasyDeepLearning.EClassifier.Train	(		self,
		eVision.EasyDeepLearning.EDataset	trainingDataset,
		eVision.EasyDeepLearning.EDataset	validationDataset,
		eVision.EasyDeepLearning.EDataAugmentation	dataAugmentation )

Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.

At the end of the training, the deep learning tool is in the state it was at the iteration that gave the minimum validation error. See eVision.EasyDeepLearning.EDeepLearningTool.BestIteration.

If no iterations is given, the training will stop automatically.

Remarks:

License(s): EasyClassify

Parameters

trainingDataset	eVision.EasyDeepLearning.EDataset with which to train the deep learning tool
validationDataset	eVision.EasyDeepLearning.EDataset with which to validate the deep learning tool
dataAugmentation	Data augmentation to use during training

◆ Train() [7/8]

None eVision.EasyDeepLearning.EClassifier.Train	(		self,
		eVision.EasyDeepLearning.EDataset	trainingDataset,
		eVision.EasyDeepLearning.EDataset	validationDataset,
		eVision.EasyDeepLearning.EDataAugmentation	dataAugmentation,
		int	iterations )

Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.

At the end of the training, the deep learning tool is in the state it was at the iteration that gave the minimum validation error. See eVision.EasyDeepLearning.EDeepLearningTool.BestIteration.

If no iterations is given, the training will stop automatically.

Remarks:

License(s): EasyClassify

Parameters

trainingDataset	eVision.EasyDeepLearning.EDataset with which to train the deep learning tool
validationDataset	eVision.EasyDeepLearning.EDataset with which to validate the deep learning tool
dataAugmentation	Data augmentation to use during training
iterations	Number of iterations for training.

◆ Train() [8/8]

None eVision.EasyDeepLearning.EClassifier.Train	(		self,
		eVision.EasyDeepLearning.EDataset	trainingDataset,
		eVision.EasyDeepLearning.EDataset	validationDataset,
		int	iterations )

Trains the eVision.EasyDeepLearning.EClassifier with the given dataset for the specified number of iterations.

At the end of the training, the deep learning tool is in the state it was at the iteration that gave the minimum validation error. See eVision.EasyDeepLearning.EDeepLearningTool.BestIteration.

If no iterations is given, the training will stop automatically.

Remarks:

License(s): EasyClassify

Parameters

trainingDataset	eVision.EasyDeepLearning.EDataset with which to train the deep learning tool
validationDataset	eVision.EasyDeepLearning.EDataset with which to validate the deep learning tool
iterations	Number of iterations for training.

Property Documentation

◆ Capacity

eVision.EasyDeepLearning.EClassifier.Capacity = property(_Capacity__getter, _Capacity__setter)

static

\endcond

Capacity of classifier to use. Be aware that changing the classifier capacity will delete the effect of any previous training. The capacity will be translated to the corresponding type (Small, Normal, or Large).

Deprecated: Deprecated in version 22.12. Scheduled to be removed in version 27.6.

◆ Channels

eVision.EasyDeepLearning.EClassifier.Channels = property(_Channels__getter, _Channels__setter)

static

\endcond

Number of channels for input images of the classifier. The number of channels can be either 1 (monochrome image) or 3 (RGB image). By default, this value will be set from the format of the first image added to the training dataset.

Remarks:

If the classifier is not trained or the value was not explicitly set, its value will be 0.

◆ ComputeHeatmapWithResult

eVision.EasyDeepLearning.EClassifier.ComputeHeatmapWithResult = property(_ComputeHeatmapWithResult__getter, _ComputeHeatmapWithResult__setter)

static

\endcond

Whether to always compute the heatmap along the result when applying the tool. If true, the heatmap is available through eVision.EasyDeepLearning.EClassificationResult.Heatmap.

◆ ComputeOODWithResult

eVision.EasyDeepLearning.EClassifier.ComputeOODWithResult = property(_ComputeOODWithResult__getter, _ComputeOODWithResult__setter)

static

\endcond

Whether to compute the OOD parameters while training. Also determines whether the OOD score is computed alongside the result when applying the tool. If true, the OOD score is available through eVision.EasyDeepLearning.EClassificationResult.OODScore.

◆ EnableAutomaticImageReformat

eVision.EasyDeepLearning.EClassifier.EnableAutomaticImageReformat = property(_EnableAutomaticImageReformat__getter, _EnableAutomaticImageReformat__setter)

static

\endcond

Enable automatic image reformat (true by default).

◆ EnableHistogramEqualization

eVision.EasyDeepLearning.EClassifier.EnableHistogramEqualization = property(_EnableHistogramEqualization__getter, _EnableHistogramEqualization__setter)

static

\endcond

Enable histogram equalization of all images passing through the classifier. (false by default)

◆ Height

eVision.EasyDeepLearning.EClassifier.Height = property(_Height__getter, _Height__setter)

static

\endcond

Height for input images of the classifier. By default, this value will be set to 224 if it wasn't explicitly set before training.

Remarks:

If the classifier is not trained or the value was not explicitly set, its value will be 0.

◆ MinimumHeight

eVision.EasyDeepLearning.EClassifier.MinimumHeight = property(_MinimumHeight__getter, None)

static

\endcond

Minimum height for input images of the classifier. This value is equal to 1 for standard networks.

◆ MinimumWidth

eVision.EasyDeepLearning.EClassifier.MinimumWidth = property(_MinimumWidth__getter, None)

static

\endcond

Minimum width for input images of the classifier. This value is equal to 1 for standard networks.

◆ ModelType

eVision.EasyDeepLearning.EClassifier.ModelType = property(_ModelType__getter, _ModelType__setter)

static

\endcond

Model type for training. Default: "Normal".

The list of available models is available through eVision.EasyDeepLearning.EClassifier.GetAvailableModelTypes.

◆ OODThreshold

eVision.EasyDeepLearning.EClassifier.OODThreshold = property(_OODThreshold__getter, _OODThreshold__setter)

static

\endcond

Out-Of-Distribution (OOD) threshold below which an image is considered to be OOD.

Remarks:

If training has been carried out with eVision.EasyDeepLearning.EClassifier.ComputeOODWithResult set to True, the parameters have been automatically initialized. Otherwise, call eVision.EasyDeepLearning.EClassifier.LearnOODParameters with the training data before calling this method.

The OOD threshold is automatically initialized during learning. If needed, the parameter can also be changed manually.

◆ ToolType

eVision.EasyDeepLearning.EClassifier.ToolType = property(_ToolType__getter, None)

static

\endcond

Type of the deep learning tool.

◆ UsePretrainedModel

eVision.EasyDeepLearning.EClassifier.UsePretrainedModel = property(_UsePretrainedModel__getter, _UsePretrainedModel__setter)

static

\endcond

Whether to use a pre-trained model when training.

Default: true if the pre-trained model are found on the disk.

◆ Width

eVision.EasyDeepLearning.EClassifier.Width = property(_Width__getter, _Width__setter)

static

\endcond

Width for input images of the classifier. By default, this value will be set to 224 if it wasn't explicitly set before training.

Remarks:

If the classifier is not trained or the value was not explicitly set, its value will be 0.

Public Member Functions

Static Public Member Functions

Protected Member Functions

Properties

Detailed Description

Constructor & Destructor Documentation

◆ __init__() [1/2]

◆ __init__() [2/2]

Member Function Documentation

◆ _Capacity__getter()

◆ _Capacity__setter()

◆ _Channels__getter()

◆ _Channels__setter()

◆ _ComputeHeatmapWithResult__getter()

◆ _ComputeHeatmapWithResult__setter()

◆ _ComputeOODWithResult__getter()

◆ _ComputeOODWithResult__setter()

◆ _EnableAutomaticImageReformat__getter()

◆ _EnableAutomaticImageReformat__setter()

◆ _EnableHistogramEqualization__getter()

◆ _EnableHistogramEqualization__setter()

◆ _Height__getter()

◆ _Height__setter()

◆ _MinimumHeight__getter()

◆ _MinimumWidth__getter()

◆ _ModelType__getter()

◆ _ModelType__setter()

◆ _OODThreshold__getter()

◆ _OODThreshold__setter()

◆ _ToolType__getter()

◆ _UsePretrainedModel__getter()

◆ _UsePretrainedModel__setter()

◆ _Width__getter()

◆ _Width__setter()

◆ Classify() [1/6]

◆ Classify() [2/6]

◆ Classify() [3/6]

◆ Classify() [4/6]

◆ Classify() [5/6]

◆ Classify() [6/6]

◆ Evaluate()

◆ GetAvailableModelTypes()

◆ GetColorizedHeatMap()

◆ GetColorizedHeatmapWithTransparency() [1/2]

◆ GetColorizedHeatmapWithTransparency() [2/2]

◆ GetHeatMap()

◆ GetNumAvailableModelTypes()

◆ GetTrainingMetrics()

◆ GetValidationMetrics()

◆ HasOODParameters()

◆ HasPretrainedModel()

◆ LearnOODParameters() [1/2]

◆ LearnOODParameters() [2/2]

◆ LoadAsPretrained()

◆ LoadOnnxModel()

◆ LoadOnnxModelAsPretrained()

◆ SerializeSettings()

◆ Train() [1/8]

◆ Train() [2/8]

◆ Train() [3/8]

◆ Train() [4/8]

◆ Train() [5/8]

◆ Train() [6/8]

◆ Train() [7/8]

◆ Train() [8/8]

Property Documentation

◆ Capacity

◆ Channels

◆ ComputeHeatmapWithResult

◆ ComputeOODWithResult

◆ EnableAutomaticImageReformat

◆ EnableHistogramEqualization

◆ Height

◆ MinimumHeight

◆ MinimumWidth

◆ ModelType

◆ OODThreshold

◆ ToolType

◆ UsePretrainedModel

◆ Width

◆ init() [1/2]

◆ init() [2/2]