XlaSparseDenseMatmulWithCsrInput

public final class XlaSparseDenseMatmulWithCsrInput

Public Methods

Output<Float>
Output<Float>
asOutput()
Returns the symbolic handle of a tensor.
static XlaSparseDenseMatmulWithCsrInput
create(Scope scope, Operand<Integer> rowPointers, Operand<Integer> sortedSampleIds, Operand<Integer> sortedTokenIds, Operand<Float> sortedGains, Operand<Float> embeddingTable, Operand<Integer> numMinibatchesPerPhysicalSparseCore, Long inputSize, Float quantizationConfigLow, Float quantizationConfigHigh, Long quantizationConfigNumBuckets, String tableName)
Factory method to create a class wrapping a new XlaSparseDenseMatmulWithCsrInput operation.

Inherited Methods

Public Methods

public Output<Float> activations ()

public Output<Float> asOutput ()

Returns the symbolic handle of a tensor.

Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

public static XlaSparseDenseMatmulWithCsrInput create (Scope scope, Operand<Integer> rowPointers, Operand<Integer> sortedSampleIds, Operand<Integer> sortedTokenIds, Operand<Float> sortedGains, Operand<Float> embeddingTable, Operand<Integer> numMinibatchesPerPhysicalSparseCore, Long inputSize, Float quantizationConfigLow, Float quantizationConfigHigh, Long quantizationConfigNumBuckets, String tableName)

Factory method to create a class wrapping a new XlaSparseDenseMatmulWithCsrInput operation.

Parameters
scope current scope
Returns
  • a new instance of XlaSparseDenseMatmulWithCsrInput