Warning: This API is deprecated and will be removed in a future version of TensorFlow after the replacement is stable.

Concat

Stay organized with collections Save and categorize content based on your preferences.
public final class Concat

Concatenates tensors along one dimension.

Public Methods

Output<T>
asOutput()
Returns the symbolic handle of a tensor.
static <T, U extends Number> Concat<T>
create(Scope scope, Iterable<Operand<T>> values, Operand<U> axis)
Factory method to create a class wrapping a new Concat operation.
Output<T>
output()
A `Tensor` with the concatenation of values stacked along the `concat_dim` dimension.

Inherited Methods

Public Methods

public Output<T> 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 Concat<T> create (Scope scope, Iterable<Operand<T>> values, Operand<U> axis)

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

Parameters
scope current scope
values List of `N` Tensors to concatenate. Their ranks and types must match, and their sizes must match in all dimensions except `concat_dim`.
axis 0-D. The dimension along which to concatenate. Must be in the range [-rank(values), rank(values)).
Returns
  • a new instance of Concat

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.