module onnxrt.ops_cpu.op_sequence_empty
#
Short summary#
module mlprodict.onnxrt.ops_cpu.op_sequence_empty
Runtime operator.
Classes#
class |
truncated documentation |
---|---|
SequenceEmpty ============= Construct an empty tensor sequence, with given data type. Attributes |
Properties#
property |
truncated documentation |
---|---|
|
Returns the list of arguments as well as the list of parameters with the default values (close to the signature). … |
|
Returns the list of modified parameters. |
|
Returns the list of optional arguments. |
|
Returns the list of optional arguments. |
|
Returns all parameters in a dictionary. |
Methods#
method |
truncated documentation |
---|---|
Documentation#
Runtime operator.
New in version 0.9.
- class mlprodict.onnxrt.ops_cpu.op_sequence_empty.SequenceEmpty(onnx_node, desc=None, **options)#
Bases:
OpRun
Construct an empty tensor sequence, with given data type.
Attributes
dtype: (Optional) The data type of the tensors in the output sequence. The default type is ‘float’. default value cannot be automatically retrieved (INT)
Outputs
output (heterogeneous)S: Empty sequence.
Type Constraints
S seq(tensor(uint8)), seq(tensor(uint16)), seq(tensor(uint32)), seq(tensor(uint64)), seq(tensor(int8)), seq(tensor(int16)), seq(tensor(int32)), seq(tensor(int64)), seq(tensor(float16)), seq(tensor(float)), seq(tensor(double)), seq(tensor(string)), seq(tensor(bool)), seq(tensor(complex64)), seq(tensor(complex128)): Constrain output types to any tensor type.
Version
Onnx name: SequenceEmpty
This version of the operator has been available since version 11.
Runtime implementation:
SequenceEmpty
- __init__(onnx_node, desc=None, **options)#
- _run(attributes=None, verbose=0, fLOG=None)#
Should be overwritten.