module onnxrt.ops_cpu.op_negative_log_likelihood_loss
#
Short summary#
module mlprodict.onnxrt.ops_cpu.op_negative_log_likelihood_loss
Runtime operator.
Classes#
class |
truncated documentation |
---|---|
Python runtime for function NegativeLogLikelihoodLoss. |
Functions#
function |
truncated documentation |
---|---|
Modified version of softmaxcrossentropy.py … |
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.
- class mlprodict.onnxrt.ops_cpu.op_negative_log_likelihood_loss.NegativeLogLikelihoodLoss(onnx_node, desc=None, **options)#
Bases:
mlprodict.onnxrt.ops_cpu._op.OpRun
Python runtime for function NegativeLogLikelihoodLoss.
- Parameters
onnx_node – onnx node
desc – internal representation
expected_attributes – expected attributes for this node
options – runtime options
- __init__(onnx_node, desc=None, **options)#
- Parameters
onnx_node – onnx node
desc – internal representation
expected_attributes – expected attributes for this node
options – runtime options
- _infer_shapes(x, target, weight=None)#
Should be overwritten.
- _infer_sizes(*args)#
Should be overwritten.
- _infer_types(x, target, weight=None)#
Should be overwritten.
- _run(x, target, weight=None)#
Should be overwritten.
- mlprodict.onnxrt.ops_cpu.op_negative_log_likelihood_loss._compute_negative_log_likelihood_loss(x, target, weight=None, reduction=b'mean', ignore_index=None)#
Modified version of softmaxcrossentropy.py to handle other type than float32.