Quantizes then dequantizes a tensor.
This is almost identical to QuantizeAndDequantizeV2, except that num_bits is a tensor, so its value can change during training.
Nested Classes
class | QuantizeAndDequantize.Options | Optional attributes for QuantizeAndDequantize
|
Constants
String | OP_NAME | The name of this op, as known by TensorFlow core engine |
Public Methods
Output<T> |
asOutput()
Returns the symbolic handle of the tensor.
|
static QuantizeAndDequantize.Options |
axis(Long axis)
|
static <T extends TNumber> QuantizeAndDequantize<T> | |
static QuantizeAndDequantize.Options |
narrowRange(Boolean narrowRange)
|
Output<T> |
output()
|
static QuantizeAndDequantize.Options |
rangeGiven(Boolean rangeGiven)
|
static QuantizeAndDequantize.Options |
signedInput(Boolean signedInput)
|
Inherited Methods
Constants
public static final String OP_NAME
The name of this op, as known by TensorFlow core engine
Public Methods
public Output<T> asOutput ()
Returns the symbolic handle of the 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 QuantizeAndDequantize<T> create (Scope scope, Operand<T> input, Operand<T> inputMin, Operand<T> inputMax, Operand<TInt32> numBits, Options... options)
Factory method to create a class wrapping a new QuantizeAndDequantize operation.
Parameters
scope | current scope |
---|---|
options | carries optional attributes values |
Returns
- a new instance of QuantizeAndDequantize