module npy.numpy_onnx_impl_body
#
Short summary#
module mlprodict.npy.numpy_onnx_impl_body
Design to implement graph as parameter.
Classes#
class |
truncated documentation |
---|---|
Class wrapping a function to make it simple as a parameter. |
|
Overloads class |
|
Overloads |
Properties#
property |
truncated documentation |
---|---|
|
Shape |
|
Size |
|
Transpose. |
Methods#
method |
truncated documentation |
---|---|
usual |
|
|
usual |
Guesses the graph inputs. |
|
|
Guesses the graph inputs. |
Converts the variable into an operator. |
|
Converts the variable into an operator. |
|
|
Converts the variable into an operator. |
Documentation#
Design to implement graph as parameter.
New in version 0.8.
- class mlprodict.npy.numpy_onnx_impl_body.AttributeGraph(fct, *inputs)#
Bases:
object
Class wrapping a function to make it simple as a parameter.
- Parameters:
New in version 0.8.
- __init__(fct, *inputs)#
- __repr__()#
usual
- _graph_guess_dtype(i, var)#
Guesses the graph inputs.
- Parameters:
i – attribute index (integer)
var – the input (
OnnxVar
)
- Returns:
input type
- to_algebra(op_version=None)#
Converts the variable into an operator.
- class mlprodict.npy.numpy_onnx_impl_body.OnnxVarGraph(*inputs, op=None, select_output=None, dtype=None, **kwargs)#
Bases:
OnnxVar
Overloads
OnnxVar
to handle graph attribute.- Parameters:
inputs – variable name or object
op – ONNX operator
select_output – if multiple output are returned by ONNX operator op, it takes only one specifed by this argument
dtype – specifies the type of the variable held by this class (op is None) in that case
fields – list of attributes with the graph type
kwargs – addition argument to give operator op
New in version 0.8.
- __init__(*inputs, op=None, select_output=None, dtype=None, **kwargs)#
- to_algebra(op_version=None)#
Converts the variable into an operator.
- class mlprodict.npy.numpy_onnx_impl_body.if_then_else(fct, *inputs)#
Bases:
AttributeGraph
Overloads class
OnnxVarGraph
.- __init__(fct, *inputs)#