tf.gather_nd(params, indices, name=None)

tf.gather_nd(params, indices, name=None)

See the guide: Tensor Transformations > Slicing and Joining

Gather values or slices from params according to indices.

params is a Tensor of rank P and indices is a Tensor of rank Q.

indices must be integer tensor, containing indices into params. It must be shape [d_0, ..., d_{Q-2}, K] where 0 < K <= P.

The innermost dimension of indices (with length K) corresponds to indices into elements (if K = P) or slices (if K < P) along the Kth dimension of params.

Produces an output tensor with shape

[d_0, ..., d_{Q-2}, params.shape[K], ..., params.shape[P-1]].

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']]

Args:

• params: A Tensor. P-D. The tensor from which to gather values.
• indices: A Tensor. Must be one of the following types: int32, int64. Q-D. Index tensor having shape [d_0, ..., d_{Q-2}, K].
• name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as params. (P+Q-K-1)-D. Values from params gathered from indices given by indices.

Defined in tensorflow/python/ops/gen_array_ops.py.