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

GatherNd

public final class GatherNd

Gather slices from `params` into a Tensor with shape specified by `indices`.

`indices` is a K-dimensional integer tensor, best thought of as a (K-1)-dimensional tensor of indices into `params`, where each element defines a slice of `params`:

output[\\(i_0, ..., i_{K-2}\\)] = params[indices[\\(i_0, ..., i_{K-2}\\)]]

Whereas in `tf.gather` `indices` defines slices into the `axis` dimension of `params`, in `tf.gather_nd`, `indices` defines slices into the first `N` dimensions of `params`, where `N = indices.shape[-1]`.

The last dimension of `indices` can be at most the rank of `params`:

indices.shape[-1] <= params.rank

The last dimension of `indices` corresponds to elements (if `indices.shape[-1] == params.rank`) or slices (if `indices.shape[-1] < params.rank`) along dimension `indices.shape[-1]` of `params`. The output tensor has shape

indices.shape[:-1] + params.shape[indices.shape[-1]:]

Note that on CPU, if an out of bound index is found, an error is returned. On GPU, if an out of bound index is found, a 0 is stored in the corresponding output value.

Some examples below.

Simple indexing into a matrix:

indices = [[0, 0], [1, 1]]
     params = [['a', 'b'], ['c', 'd']]
     output = ['a', 'd']
 
Slice indexing into a matrix:
indices = [[1], [0]]
     params = [['a', 'b'], ['c', 'd']]
     output = [['c', 'd'], ['a', 'b']]
 
Indexing into a 3-tensor:
indices = [[1]]
     params = [[['a0', 'b0'], ['c0', 'd0']],
               [['a1', 'b1'], ['c1', 'd1']]]
     output = [[['a1', 'b1'], ['c1', 'd1']]]
 
 
     indices = [[0, 1], [1, 0]]
     params = [[['a0', 'b0'], ['c0', 'd0']],
               [['a1', 'b1'], ['c1', 'd1']]]
     output = [['c0', 'd0'], ['a1', 'b1']]
 
 
     indices = [[0, 0, 1], [1, 0, 1]]
     params = [[['a0', 'b0'], ['c0', 'd0']],
               [['a1', 'b1'], ['c1', 'd1']]]
     output = ['b0', 'b1']
 
Batched indexing into a matrix:
indices = [[[0, 0]], [[0, 1]]]
     params = [['a', 'b'], ['c', 'd']]
     output = [['a'], ['b']]
 
Batched slice indexing into a matrix:
indices = [[[1]], [[0]]]
     params = [['a', 'b'], ['c', 'd']]
     output = [[['c', 'd']], [['a', 'b']]]
 
Batched indexing into a 3-tensor:
indices = [[[1]], [[0]]]
     params = [[['a0', 'b0'], ['c0', 'd0']],
               [['a1', 'b1'], ['c1', 'd1']]]
     output = [[[['a1', 'b1'], ['c1', 'd1']]],
               [[['a0', 'b0'], ['c0', 'd0']]]]
 
     indices = [[[0, 1], [1, 0]], [[0, 0], [1, 1]]]
     params = [[['a0', 'b0'], ['c0', 'd0']],
               [['a1', 'b1'], ['c1', 'd1']]]
     output = [[['c0', 'd0'], ['a1', 'b1']],
               [['a0', 'b0'], ['c1', 'd1']]]
 
 
     indices = [[[0, 0, 1], [1, 0, 1]], [[0, 1, 1], [1, 1, 0]]]
     params = [[['a0', 'b0'], ['c0', 'd0']],
               [['a1', 'b1'], ['c1', 'd1']]]
     output = [['b0', 'b1'], ['d0', 'c1']]
 
See also `tf.gather` and `tf.batch_gather`.

Public Methods

Output<T>
asOutput()
Returns the symbolic handle of a tensor.
static <T, U extends Number> GatherNd<T>
create(Scope scope, Operand<T> params, Operand<U> indices)
Factory method to create a class wrapping a new GatherNd operation.
Output<T>
output()
Values from `params` gathered from indices given by `indices`, with shape `indices.shape[:-1] + params.shape[indices.shape[-1]:]`.

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 GatherNd<T> create (Scope scope, Operand<T> params, Operand<U> indices)

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

Parameters
scope current scope
params The tensor from which to gather values.
indices Index tensor.
Returns
  • a new instance of GatherNd

public Output<T> output ()

Values from `params` gathered from indices given by `indices`, with shape `indices.shape[:-1] + params.shape[indices.shape[-1]:]`.