Concatenates quantized tensors along one dimension.
Public Methods
static <T> QuantizedConcat<T> | |
Output<T> |
output()
A `Tensor` with the concatenation of values stacked along the
`concat_dim` dimension.
|
Output<Float> |
outputMax()
The float value that the maximum quantized output value represents.
|
Output<Float> |
outputMin()
The float value that the minimum quantized output value represents.
|
Inherited Methods
Public Methods
public static QuantizedConcat<T> create (Scope scope, Operand<Integer> concatDim, Iterable<Operand<T>> values, Iterable<Operand<Float>> inputMins, Iterable<Operand<Float>> inputMaxes)
Factory method to create a class wrapping a new QuantizedConcat operation.
Parameters
scope | current scope |
---|---|
concatDim | 0-D. The dimension along which to concatenate. Must be in the range [0, rank(values)). |
values | The `N` Tensors to concatenate. Their ranks and types must match, and their sizes must match in all dimensions except `concat_dim`. |
inputMins | The minimum scalar values for each of the input tensors. |
inputMaxes | The maximum scalar values for each of the input tensors. |
Returns
- a new instance of QuantizedConcat
public Output<T> output ()
A `Tensor` with the concatenation of values stacked along the `concat_dim` dimension. This tensor's shape matches that of `values` except in `concat_dim` where it has the sum of the sizes.
public Output<Float> outputMax ()
The float value that the maximum quantized output value represents.
public Output<Float> outputMin ()
The float value that the minimum quantized output value represents.