FeatureVectorizer#

Domain: ai.onnx.ml
Since version: 1

Concatenates input tensors into one continuous output. All input shapes are 2-D and are concatenated along the second dimension. 1-D tensors are treated as [1,C]. Inputs are copied to the output maintaining the order of the input arguments. All inputs must be integers or floats, while the output will be all floating point values.

Inputs

X (T1): An ordered collection of tensors, all with the same element type.

Outputs

Y (tensor(float)): The output array, elements ordered as the inputs.

Type Constraints

T1: The input type must be a tensor of a numeric type. Allowed types: tensor(double), tensor(float), tensor(int32), tensor(int64).

Examples#

test_cc_feature_vectorizer_mixed_dtypes

Node:
  ai.onnx.ml.FeatureVectorizer(x0, x1) -> (y)
  Attributes:
    inputdimensions = [2, 2]

Inputs:
  x0: shape=(1, 2), dtype=int64
    [[1, 2]]
  x1: shape=(1, 2), dtype=float32
    [[3.5, 4.5]]

Outputs:
  y: shape=(1, 4), dtype=float32
    [[1. , 2. , 3.5, 4.5]]

test_cc_feature_vectorizer_two_float

Node:
  ai.onnx.ml.FeatureVectorizer(x0, x1) -> (y)
  Attributes:
    inputdimensions = [2, 1]

Inputs:
  x0: shape=(2, 2), dtype=float32
    [[1., 2.],
     [3., 4.]]
  x1: shape=(2, 1), dtype=float32
    [[10.],
     [20.]]

Outputs:
  y: shape=(2, 3), dtype=float32
    [[ 1.,  2., 10.],
     [ 3.,  4., 20.]]