ArrayFeatureExtractor#

Domain: ai.onnx.ml
Since version: 1

Select elements of the input tensor based on the indices passed. The indices are applied to the last axes of the tensor.

Inputs

X (T): Data to be selected
Y (tensor(int64)): The indices, based on 0 as the first index of any dimension.

Outputs

Z (T): Selected output data as an array

Type Constraints

T: The input must be a tensor of a numeric type or string. The output will be of the same tensor type. Allowed types: tensor(double), tensor(float), tensor(int32), tensor(int64), tensor(string).

Examples#

test_ai_onnx_ml_array_feature_extractor

Node:
  ai.onnx.ml.ArrayFeatureExtractor(x, y) -> (z)

Inputs:
  x: shape=(3, 4), dtype=float32
    [[ 0.,  1.,  2.,  3.],
     [10., 11., 12., 13.],
     [20., 21., 22., 23.]]
  y: shape=(3,), dtype=int64
    [0, 2, 3]

Outputs:
  z: shape=(3, 3), dtype=float32
    [[ 0.,  2.,  3.],
     [10., 12., 13.],
     [20., 22., 23.]]