ai.onnx.ml - ArrayFeatureExtractor¶
ArrayFeatureExtractor - 1 (ai.onnx.ml)¶
Version¶
domain:
ai.onnx.ml
since_version:
1
function:
False
support_level:
SupportType.COMMON
shape inference:
True
This version of the operator has been available since version 1 of domain ai.onnx.ml.
Summary¶
Select elements of the input tensor based on the indices passed.
The indices are applied to the last axes of the tensor.
Inputs¶
X (heterogeneous) - T:
Data to be selected
Y (heterogeneous) - tensor(int64):
The indices, based on 0 as the first index of any dimension.
Outputs¶
Z (heterogeneous) - T:
Selected output data as an array
Type Constraints¶
T in (
tensor(double)
,tensor(float)
,tensor(int32)
,tensor(int64)
,tensor(string)
):The input must be a tensor of a numeric type or string. The output will be of the same tensor type.
Examples¶
default¶
import numpy as np
import onnx
node = onnx.helper.make_node(
"ArrayFeatureExtractor",
inputs=["x", "y"],
outputs=["z"],
domain="ai.onnx.ml",
)
x = np.arange(12).reshape((3, 4)).astype(np.float32)
y = np.array([0, 1], dtype=np.int64)
z = np.array([[0, 4, 8], [1, 5, 9]], dtype=np.float32).T
expect(
node,
inputs=[x, y],
outputs=[z],
name="test_ai_onnx_ml_array_feature_extractor",
)