Python* API Reference for Intel® Data Analytics Acceleration Library 2020 Update 1

Public Member Functions | Static Public Attributes | List of all members
Batch Class Reference

Provides methods for the forward softmax cross layer in the batch processing mode. More...

Public Member Functions

def __init__
 
def getMethod
 
def getLayerInput
 
def getLayerParameter
 
def getLayerResult
 
def getResult
 
def setResult
 
def clone
 
def allocateResult
 
def getLayerForPrediction
 
def compute
 
- Public Member Functions inherited from Batch
def clone
 
- Public Member Functions inherited from LayerIface
def getLayerResult
 
def getLayerInput
 
def getLayerParameter
 
def clone
 
def allocateResult
 
def allocateInput
 
def initializeInput
 
def addInput
 
def getLayerForPrediction
 
- Public Member Functions inherited from AlgorithmImpl
def computeNoThrow
 
def compute
 
def checkComputeParams
 
def checkResult
 
def setupCompute
 
def resetCompute
 
def enableResetOnCompute
 
def hostApp
 
def setHostApp
 
- Public Member Functions inherited from Algorithm
def checkComputeParams
 
def getBaseParameter
 
- Public Member Functions inherited from AlgorithmIfaceImpl
def enableChecks
 
def isChecksEnabled
 
- Public Member Functions inherited from AlgorithmIface
def checkComputeParams
 
def checkResult
 
def getMethod
 

Static Public Attributes

 parameter = ...
 
 input = ...
 

Detailed Description

Parameters
fptypeData type to use in intermediate computations for the forward softmax cross-entropy layer, double or float
methodForward softmax cross-entropy layer method, Method
Enumerations
  • Method Computation methods for the forward softmax cross-entropy layer
  • forward.InputId Identifiers of input objects for the forward softmax cross-entropy layer
  • forward.ResultId Identifiers of result objects for the forward softmax cross-entropy layer
  • forward.ResultLayerDataId Identifiers of extra results computed by the forward softmax cross-entropy layer
  • LayerDataId Identifiers of collection in result objects for the forward softmax cross-entropy layer
References
Deprecated:
This item will be removed in a future release.
Aliases
  • Batch_Float64DefaultDense is an alias of Batch(fptype=float64, method=daal.algorithms.neural_networks.layers.loss.softmax_cross.defaultDense)
  • Batch_Float32DefaultDense is an alias of Batch(fptype=float32, method=daal.algorithms.neural_networks.layers.loss.softmax_cross.defaultDense)

Constructor & Destructor Documentation

def __init__ (   self,
  args 
)

Variant 1

Default constructor

Deprecated:
This item will be removed in a future release.

Variant 2

Constructs a forward softmax cross-entropy layer in the batch processing mode and initializes its parameter with the provided parameter

Parameters
parameterParameter to initialize the parameter of the layer
Deprecated:
This item will be removed in a future release.

Variant 3

Constructs a forward softmax cross-entropy layer by copying input objects and parameters of another forward softmax cross-entropy layer in the batch processing mode

Parameters
otherAlgorithm to use as the source to initialize the input objects and parameters of the layer
Deprecated:
This item will be removed in a future release.

Member Function Documentation

def allocateResult (   self)

Allocates memory to store the result of the forward softmax cross-entropy layer

Returns
Status of computations
Deprecated:
This item will be removed in a future release.
def clone (   self)

Returns a pointer to a newly allocated forward softmax cross-entropy layer with a copy of the input objects and parameters for this forward softmax cross-entropy layer in the batch processing mode

Returns
Pointer to the newly allocated algorithm
Deprecated:
This item will be removed in a future release.
def compute (   self)

Invokes computations

def getLayerForPrediction (   self)

Returns forward softmax layer - the layer that corresponds to this layer on the prediction stage

Returns
Forward softmax layer
Deprecated:
This item will be removed in a future release.
def getLayerInput (   self)

Returns the structure that contains the input objects of the forward softmax cross-entropy layer

Returns
Structure that contains the input objects of the forward softmax cross-entropy layer
Deprecated:
This item will be removed in a future release.
def getLayerParameter (   self)

Returns the structure that contains the parameters of the forward softmax cross-entropy layer

Returns
Structure that contains the parameters of the forward softmax cross-entropy layer
Deprecated:
This item will be removed in a future release.
def getLayerResult (   self)

Returns the structure that contains result of the forward softmax cross-entropy layer

Returns
Structure that contains result of the forward softmax cross-entropy layer
Deprecated:
This item will be removed in a future release.
def getMethod (   self)

Returns the method of the layer

Returns
Method of the layer
Deprecated:
This item will be removed in a future release.
def getResult (   self)

Returns the structure that contains the result of the forward softmax cross-entropy layer

Returns
Structure that contains the result of the forward softmax cross-entropy layer
Deprecated:
This item will be removed in a future release.
def setResult (   self,
  result 
)

Registers user-allocated memory to store the result of the forward softmax cross-entropy layer

Parameters
resultStructure to store the result of the forward softmax cross-entropy layer
Returns
Status of computations
Deprecated:
This item will be removed in a future release.

Member Data Documentation

input = ...
static

Forward softmax cross-entropy layer input

parameter = ...
static

Forward softmax cross-entropy layer parameters


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

For more complete information about compiler optimizations, see our Optimization Notice.