T
- data type for output()
output@Operator public final class Squeeze<T> extends PrimitiveOp implements Operand<T>
Given a tensor `input`, this operation returns a tensor of the same type with all dimensions of size 1 removed. If you don't want to remove all size 1 dimensions, you can remove specific size 1 dimensions by specifying `axis`.
For example:
# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]
shape(squeeze(t)) ==> [2, 3]
Or, to remove specific size 1 dimensions:
# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]
shape(squeeze(t, [2, 4])) ==> [1, 2, 3, 1]
Modifier and Type | Class and Description |
---|---|
static class |
Squeeze.Options
Optional attributes for
Squeeze |
operation
Modifier and Type | Method and Description |
---|---|
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static Squeeze.Options |
axis(List<Long> axis) |
static <T> Squeeze<T> |
create(Scope scope,
Operand<T> input,
Squeeze.Options... options)
Factory method to create a class wrapping a new Squeeze operation.
|
Output<T> |
output()
Contains the same data as `input`, but has one or more dimensions of
size 1 removed.
|
equals, hashCode, op, toString
public static <T> Squeeze<T> create(Scope scope, Operand<T> input, Squeeze.Options... options)
scope
- current scopeinput
- The `input` to squeeze.options
- carries optional attributes valuespublic static Squeeze.Options axis(List<Long> axis)
axis
- If specified, only squeezes the dimensions listed. The dimension
index starts at 0. It is an error to squeeze a dimension that is not 1. Must
be in the range `[-rank(input), rank(input))`.public Output<T> output()
public Output<T> asOutput()
Operand
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.
asOutput
in interface Operand<T>
OperationBuilder.addInput(Output)
Copyright © 2022. All rights reserved.