QuantizedBiasAdd

public final class QuantizedBiasAdd

Adds Tensor 'bias' to Tensor 'input' for Quantized types.

Broadcasts the values of bias on dimensions 0..N-2 of 'input'.

Constants

String OP_NAME The name of this op, as known by TensorFlow core engine

Public Methods

static <V extends TType> QuantizedBiasAdd<V>
create(Scope scope, Operand<? extends TType> input, Operand<? extends TType> bias, Operand<TFloat32> minInput, Operand<TFloat32> maxInput, Operand<TFloat32> minBias, Operand<TFloat32> maxBias, Class<V> outType)
Factory method to create a class wrapping a new QuantizedBiasAdd operation.
Output<TFloat32>
maxOut()
The float value that the highest quantized output value represents.
Output<TFloat32>
minOut()
The float value that the lowest quantized output value represents.
Output<V>
output()

Inherited Methods

Constants

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

Constant Value: "QuantizedBiasAdd"

Public Methods

public static QuantizedBiasAdd<V> create (Scope scope, Operand<? extends TType> input, Operand<? extends TType> bias, Operand<TFloat32> minInput, Operand<TFloat32> maxInput, Operand<TFloat32> minBias, Operand<TFloat32> maxBias, Class<V> outType)

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

Parameters
scope current scope
bias A 1D bias Tensor with size matching the last dimension of 'input'.
minInput The float value that the lowest quantized input value represents.
maxInput The float value that the highest quantized input value represents.
minBias The float value that the lowest quantized bias value represents.
maxBias The float value that the highest quantized bias value represents.
Returns
  • a new instance of QuantizedBiasAdd

public Output<TFloat32> maxOut ()

The float value that the highest quantized output value represents.

public Output<TFloat32> minOut ()

The float value that the lowest quantized output value represents.

public Output<V> output ()