Java* API Reference for Intel® Data Analytics Acceleration Library 2019

Classes

Contains classes of the two-dimensional (2D) locally connected layer.

Classes

class  LocallyConnected2dBackwardBatch
 Class that computes the results of the 2D locally connected layer in the batch processing mode. More...
 
class  LocallyConnected2dBackwardInput
 Input object for the backward 2D locally connected layer. More...
 
class  LocallyConnected2dBackwardResult
 Provides methods to access results obtained with the compute() method of the backward 2D locally connected layer. More...
 
class  LocallyConnected2dBatch
 Provides methods for the 2D locally connected layer in the batch processing mode. More...
 
class  LocallyConnected2dForwardBatch
 Class that computes the results of the forward 2D locally connected layer in the batch processing mode. More...
 
class  LocallyConnected2dForwardInput
 Input object for the forward 2D locally connected layer More...
 
class  LocallyConnected2dForwardResult
 Class that provides methods to access the result obtained with the compute() method of the forward 2D locally connected layer. More...
 
class  LocallyConnected2dIndices
 Data structure representing the dimension for locally connected kernels. More...
 
class  LocallyConnected2dKernelSizes
 Data structure representing the sizes of the two-dimensional kernel subtensor for the backward 2D locally connected layer and results for the forward 2D locally connected layer. More...
 
class  LocallyConnected2dLayerDataId
 Identifiers of input objects for the backward 2D locally connected layer and results for the forward 2D locally connected layer. More...
 
class  LocallyConnected2dMethod
 Available methods for the 2D locally connected layer. More...
 
class  LocallyConnected2dPaddings
 Data structure representing the number of data to be implicitly added to the subtensor. More...
 
class  LocallyConnected2dParameter
 Class that specifies parameters of the 2D locally connected layer. More...
 
class  LocallyConnected2dStrides
 Data structure representing the intervals on which the kernel should be applied to the input. More...
 

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