module onnxrt.ops_cpu.op_array_feature_extractor

Short summary

module mlprodict.onnxrt.ops_cpu.op_array_feature_extractor

Runtime operator.

source on GitHub

Classes

class	truncated documentation
ArrayFeatureExtractor	ArrayFeatureExtractor (ai.onnx.ml) ================================== Select elements of the input tensor based on the …

Functions

function	truncated documentation
_array_feature_extrator	Implementation of operator ArrayFeatureExtractor with numpy.
sizeof_dtype

Properties

property	truncated documentation
args_default	Returns the list of arguments as well as the list of parameters with the default values (close to the signature). …
args_default_modified	Returns the list of modified parameters.
args_mandatory	Returns the list of optional arguments.
args_optional	Returns the list of optional arguments.
atts_value	Returns all parameters in a dictionary.

Methods

method	truncated documentation
__init__
_infer_shapes	Infer the shapes for the output.
_infer_types	Returns the type of the output.
_run	Runtime for operator ArrayFeatureExtractor.

Documentation

Runtime operator.

source on GitHub

class mlprodict.onnxrt.ops_cpu.op_array_feature_extractor.ArrayFeatureExtractor(ai.onnx.ml)

Bases: mlprodict.onnxrt.ops_cpu._op.OpRun

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

Version

Onnx name: ArrayFeatureExtractor

This version of the operator has been available since version 1 of domain ai.onnx.ml.

Runtime implementation: ArrayFeatureExtractor

Parameters

• onnx_node – onnx node

• desc – internal representation

• expected_attributes – expected attributes for this node

• options – runtime options

source on GitHub

__init__(onnx_node, desc=None, **options)

Parameters

• onnx_node – onnx node

• desc – internal representation

• expected_attributes – expected attributes for this node

• options – runtime options

source on GitHub

_infer_shapes(data, indices)

Infer the shapes for the output.

source on GitHub

_infer_types(data, indices)

Returns the type of the output.

source on GitHub

_run(data, indices)

Runtime for operator ArrayFeatureExtractor.

Warning

ONNX specifications may be imprecise in some cases. When the input data is a vector (one dimension), the output has still two like a matrix with one row. The implementation follows what onnxruntime does in array_feature_extractor.cc.

source on GitHub

mlprodict.onnxrt.ops_cpu.op_array_feature_extractor._array_feature_extrator(data, indices)

Implementation of operator ArrayFeatureExtractor with numpy.

source on GitHub

previous

module onnxrt.ops_cpu.op_argmin

next

module onnxrt.ops_cpu.op_asin