GatherND - version 11#
This page documents version 11 of operator GatherND. See GatherND for the latest version (since version 13).
Domain:
ai.onnxSince version: 11
Given data tensor of rank r >= 1, and indices tensor of rank q >= 1, this operator gathers
slices of data into an output tensor of rank q + r - indices_shape[-1] - 1.
indices is an q-dimensional integer tensor, best thought of as a (q-1)-dimensional tensor of index-tuples into data,
where each element defines a slice of data
Some salient points about the inputs’ rank and shape:
r >= 1 and q >= 1 are to be honored. There is no dependency condition to be met between ranks
randqThe
indices_shape[-1]should have a value between 1 (inclusive) and rankr(inclusive)All values in
indicesare expected to be within bounds [-s, s-1] along axis of sizes(i.e.)-data_shape[i] r=> error condition
If
indices_shape[-1] == r, since the rank ofindicesisq,indicescan be thought of as a(q-1)-dimensional tensor containing 1-D tensors of dimensionr. Let us think of each suchrranked tensor asindices_slice. Each *scalar value* corresponding todata[indices_slice]is filled into the corresponding location of the(q-1)-dimensional tensor to form theoutputtensor (Example 1 below)If
indices_shape[-1] < r, since the rank ofindicesisq,indicescan be thought of as a(q-1)-dimensional tensor containing 1-D tensors of dimension< r. Let us think of each such tensors asindices_slice. Each *tensor slice* corresponding todata[indices_slice , :]is filled into the corresponding location of the(q-1)-dimensional tensor to form theoutputtensor (Examples 2, 3, and 4 below)
This operator is the inverse of ScatterND.
Example 1
data = [[0,1],[2,3]] # data_shape = [2, 2]
indices = [[0,0],[1,1]] # indices_shape = [2, 2]
output = [0,3] # output_shape = [2]
Example 2
data = [[0,1],[2,3]] # data_shape = [2, 2]
indices = [[1],[0]] # indices_shape = [2, 1]
output = [[2,3],[0,1]] # output_shape = [2, 2]
Example 3
data = [[[0,1],[2,3]],[[4,5],[6,7]]] # data_shape = [2, 2, 2]
indices = [[0,1],[1,0]] # indices_shape = [2, 2]
output = [[2,3],[4,5]] # output_shape = [2, 2]
Example 4
data = [[[0,1],[2,3]],[[4,5],[6,7]]] # data_shape = [2, 2, 2]
indices = [[[0,1]],[[1,0]]] # indices_shape = [2, 1, 2]
output = [[[2,3]],[[4,5]]] # output_shape = [2, 1, 2]
Inputs
data (T): Tensor of rank r >= 1.
indices (tensor(int64)): Tensor of rank q >= 1. All index values are expected to be within bounds [-s, s-1] along axis of size s. It is an error if any of the index values are out of bounds.
Outputs
output (T): Tensor of rank q + r - indices_shape[-1] - 1.
Type Constraints
T: Constrain input and output types to any tensor type. Allowed types: tensor(bool), tensor(complex128), tensor(complex64), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8).