Inheritance diagram for Synapse.ML.Onnx.ONNXModel:

[legend]

Collaboration diagram for Synapse.ML.Onnx.ONNXModel:

[legend]

Public Member Functions
	ONNXModel ()
	Creates a ONNXModel without any parameters. More...

	ONNXModel (string uid)
	Creates a ONNXModel with a UID that is used to give the ONNXModel a unique ID. More...

ONNXModel	SetArgMaxDict (Dictionary< string, string > value)
	Sets value for argMaxDict More...

ONNXModel	SetDeviceType (string value)
	Sets value for deviceType More...

ONNXModel	SetFeedDict (Dictionary< string, string > value)
	Sets value for feedDict More...

ONNXModel	SetFetchDict (Dictionary< string, string > value)
	Sets value for fetchDict More...

ONNXModel	SetMiniBatcher (JavaTransformer value)
	Sets value for miniBatcher More...

ONNXModel	SetModelPayload (object value)
	Sets value for modelPayload More...

ONNXModel	SetOptimizationLevel (string value)
	Sets value for optimizationLevel More...

ONNXModel	SetSoftMaxDict (Dictionary< string, string > value)
	Sets value for softMaxDict More...

Dictionary< string, string >	GetArgMaxDict ()
	Gets argMaxDict value More...

string	GetDeviceType ()
	Gets deviceType value More...

Dictionary< string, string >	GetFeedDict ()
	Gets feedDict value More...

Dictionary< string, string >	GetFetchDict ()
	Gets fetchDict value More...

JavaTransformer	GetMiniBatcher ()
	Gets miniBatcher value More...

object	GetModelPayload ()
	Gets modelPayload value More...

string	GetOptimizationLevel ()
	Gets optimizationLevel value More...

Dictionary< string, string >	GetSoftMaxDict ()
	Gets softMaxDict value More...

void	Save (string path)
	Saves the object so that it can be loaded later using Load. Note that these objects can be shared with Scala by Loading or Saving in Scala. More...

JavaMLWriter	Write ()
	Returns a JavaMLWriter instance for this ML instance.

JavaMLReader< ONNXModel >	Read ()
	Get the corresponding JavaMLReader instance. More...

Static Public Member Functions
static ONNXModel	Load (string path)
	Loads the ONNXModel that was previously saved using Save(string). More...

Detailed Description

ONNXModel implements ONNXModel

Constructor & Destructor Documentation

◆ ONNXModel() [1/2]

Synapse.ML.Onnx.ONNXModel.ONNXModel ( )

inline

Creates a ONNXModel without any parameters.

◆ ONNXModel() [2/2]

Synapse.ML.Onnx.ONNXModel.ONNXModel ( string uid )

inline

Creates a ONNXModel with a UID that is used to give the ONNXModel a unique ID.

Parameters

uid	An immutable unique ID for the object and its derivatives.

Member Function Documentation

◆ GetArgMaxDict()

Dictionary<string, string> Synapse.ML.Onnx.ONNXModel.GetArgMaxDict ( )

inline

Gets argMaxDict value

Returns: argMaxDict: A map between output dataframe columns, where the value column will be computed from taking the argmax of the key column. This can be used to convert probability output to predicted label.

◆ GetDeviceType()

string Synapse.ML.Onnx.ONNXModel.GetDeviceType ( )

Gets deviceType value

Returns: deviceType: Specify a device type the model inference runs on. Supported types are: CPU or CUDA.If not specified, auto detection will be used.

◆ GetFeedDict()

Dictionary<string, string> Synapse.ML.Onnx.ONNXModel.GetFeedDict ( )

inline

Gets feedDict value

Returns: feedDict: Provide a map from CNTK/ONNX model input variable names (keys) to column names of the input dataframe (values)

◆ GetFetchDict()

Dictionary<string, string> Synapse.ML.Onnx.ONNXModel.GetFetchDict ( )

inline

Gets fetchDict value

Returns: fetchDict: Provide a map from column names of the output dataframe (keys) to CNTK/ONNX model output variable names (values)

◆ GetMiniBatcher()

JavaTransformer Synapse.ML.Onnx.ONNXModel.GetMiniBatcher ( )

inline

Gets miniBatcher value

Returns: miniBatcher: Minibatcher to use

◆ GetModelPayload()

object Synapse.ML.Onnx.ONNXModel.GetModelPayload ( )

Gets modelPayload value

Returns: modelPayload: Array of bytes containing the serialized ONNX model.

◆ GetOptimizationLevel()

string Synapse.ML.Onnx.ONNXModel.GetOptimizationLevel ( )

Gets optimizationLevel value

Returns: optimizationLevel: Specify the optimization level for the ONNX graph optimizations. Details at https://onnxruntime.ai/docs/resources/graph-optimizations.html#graph-optimization-levels. Supported values are: NO_OPT; BASIC_OPT; EXTENDED_OPT; ALL_OPT. Default: ALL_OPT.

◆ GetSoftMaxDict()

Dictionary<string, string> Synapse.ML.Onnx.ONNXModel.GetSoftMaxDict ( )

inline

Gets softMaxDict value

Returns: softMaxDict: A map between output dataframe columns, where the value column will be computed from taking the softmax of the key column. If the 'rawPrediction' column contains logits outputs, then one can set softMaxDict to Map("rawPrediction" -> "probability") to obtain the probability outputs.

◆ Load()

static ONNXModel Synapse.ML.Onnx.ONNXModel.Load ( string path )

static

Loads the ONNXModel that was previously saved using Save(string).

Parameters

path	The path the previous ONNXModel was saved to

Returns: New ONNXModel object, loaded from path.

◆ Read()

JavaMLReader<ONNXModel> Synapse.ML.Onnx.ONNXModel.Read ( )

Get the corresponding JavaMLReader instance.

Returns: an JavaMLReader<ONNXModel> instance for this ML instance.

◆ Save()

void Synapse.ML.Onnx.ONNXModel.Save ( string path )

Saves the object so that it can be loaded later using Load. Note that these objects can be shared with Scala by Loading or Saving in Scala.

Parameters

path	The path to save the object to

◆ SetArgMaxDict()

ONNXModel Synapse.ML.Onnx.ONNXModel.SetArgMaxDict ( Dictionary< string, string > value )

Sets value for argMaxDict

Parameters

value A map between output dataframe columns, where the value column will be computed from taking the argmax of the key column. This can be used to convert probability output to predicted label.

Returns: New ONNXModel object

◆ SetDeviceType()

ONNXModel Synapse.ML.Onnx.ONNXModel.SetDeviceType ( string value )

Sets value for deviceType

Parameters

value Specify a device type the model inference runs on. Supported types are: CPU or CUDA.If not specified, auto detection will be used.

Returns: New ONNXModel object

◆ SetFeedDict()

ONNXModel Synapse.ML.Onnx.ONNXModel.SetFeedDict ( Dictionary< string, string > value )

Sets value for feedDict

Parameters

value Provide a map from CNTK/ONNX model input variable names (keys) to column names of the input dataframe (values)

Returns: New ONNXModel object

◆ SetFetchDict()

ONNXModel Synapse.ML.Onnx.ONNXModel.SetFetchDict ( Dictionary< string, string > value )

Sets value for fetchDict

Parameters

value Provide a map from column names of the output dataframe (keys) to CNTK/ONNX model output variable names (values)

Returns: New ONNXModel object

◆ SetMiniBatcher()

ONNXModel Synapse.ML.Onnx.ONNXModel.SetMiniBatcher ( JavaTransformer value )

Sets value for miniBatcher

Parameters

value Minibatcher to use

Returns: New ONNXModel object

◆ SetModelPayload()

ONNXModel Synapse.ML.Onnx.ONNXModel.SetModelPayload ( object value )

Sets value for modelPayload

Parameters

value Array of bytes containing the serialized ONNX model.

Returns: New ONNXModel object

◆ SetOptimizationLevel()

ONNXModel Synapse.ML.Onnx.ONNXModel.SetOptimizationLevel ( string value )

Sets value for optimizationLevel

Parameters

value Specify the optimization level for the ONNX graph optimizations. Details at https://onnxruntime.ai/docs/resources/graph-optimizations.html#graph-optimization-levels. Supported values are: NO_OPT; BASIC_OPT; EXTENDED_OPT; ALL_OPT. Default: ALL_OPT.

Returns: New ONNXModel object

◆ SetSoftMaxDict()

ONNXModel Synapse.ML.Onnx.ONNXModel.SetSoftMaxDict ( Dictionary< string, string > value )

Sets value for softMaxDict

Parameters

value A map between output dataframe columns, where the value column will be computed from taking the softmax of the key column. If the 'rawPrediction' column contains logits outputs, then one can set softMaxDict to Map("rawPrediction" -> "probability") to obtain the probability outputs.

Returns: New ONNXModel object

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

synapse/ml/onnx/ONNXModel.cs

Public Member Functions

Static Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ ONNXModel() [1/2]

◆ ONNXModel() [2/2]

Member Function Documentation

◆ GetArgMaxDict()

◆ GetDeviceType()

◆ GetFeedDict()

◆ GetFetchDict()

◆ GetMiniBatcher()

◆ GetModelPayload()

◆ GetOptimizationLevel()

◆ GetSoftMaxDict()

◆ Load()

◆ Read()

◆ Save()

◆ SetArgMaxDict()

◆ SetDeviceType()

◆ SetFeedDict()

◆ SetFetchDict()

◆ SetMiniBatcher()

◆ SetModelPayload()

◆ SetOptimizationLevel()

◆ SetSoftMaxDict()