fiftyone.operators.evaluation_metric.EvaluationMetric

class documentation

class EvaluationMetric(Operator): (source)

Base class for evaluation metric operators.

Method	`cleanup`	Cleans up the results of the evaluation metric with the given key from the collection.
Method	`compute`	Computes the evaluation metric for the given collection.
Method	`get_fields`	Lists the fields that were populated by the evaluation metric with the given key, if any.
Method	`get_parameters`	Defines any necessary properties to collect this evaluation metric's parameters from a user during prompting.
Method	`parse_parameters`	Performs any necessary execution-time formatting to this evaluation metric's parameters.
Method	`rename`	Performs any necessary operations required to rename this evaluation metric's key.

Inherited from Operator:

Method	`__init__`	Undocumented
Method	`add_secrets`	Adds secrets to the operator.
Method	`execute`	Executes the operator.
Method	`method_to_uri`	Converts a method name to a URI.
Method	`resolve_delegation`	Returns the resolved forced delegation flag.
Method	`resolve_execution_options`	Returns the resolved execution options.
Method	`resolve_input`	Returns the resolved input property.
Method	`resolve_output`	Returns the resolved output property.
Method	`resolve_placement`	Returns the resolved placement of the operator.
Method	`resolve_type`	Returns the resolved input or output property.
Method	`to_json`	Returns a JSON representation of the operator.
Instance Variable	`plugin_name`	Undocumented
Property	`builtin`	Whether the operator is builtin.
Property	`config`	The `OperatorConfig` for the operator.
Property	`name`	Undocumented
Property	`uri`	The unique identifier of the operator: `plugin_name/operator_name`.
Instance Variable	`_builtin`	Undocumented
Instance Variable	`_plugin_secrets`	Undocumented

def cleanup(self, samples, config, eval_key): (source) ¶

Cleans up the results of the evaluation metric with the given key from the collection.

Parameters
samples	a `fiftyone.core.collections.SampleCollection`
config	an `fiftyone.core.evaluation.EvaluationMethodConfig`
eval_key	an evaluation key

def compute(self, samples, results, **kwargs): (source) ¶

Computes the evaluation metric for the given collection.

Parameters
samples	a `fiftyone.core.collections.SampleCollection`
results	an `fiftyone.core.evaluation.EvaluationResults`
**kwargs	arbitrary metric-specific parameters
Returns
an optional aggregate metric value to store on the results

def get_fields(self, samples, config, eval_key): (source) ¶

Lists the fields that were populated by the evaluation metric with the given key, if any.

Parameters
samples	a `fiftyone.core.collections.SampleCollection`
config	an `fiftyone.core.evaluation.EvaluationMethodConfig`
eval_key	an evaluation key
Returns
a list of fields

def get_parameters(self, ctx, inputs): (source) ¶

Defines any necessary properties to collect this evaluation metric's parameters from a user during prompting.

Parameters
ctx	an `fiftyone.operators.ExecutionContext`
inputs	a `fiftyone.operators.types.Property`

def parse_parameters(self, ctx, params): (source) ¶

Performs any necessary execution-time formatting to this evaluation metric's parameters.

Parameters
ctx	an `fiftyone.operators.ExecutionContext`
params	a params dict

def rename(self, samples, config, eval_key, new_eval_key): (source) ¶

Performs any necessary operations required to rename this evaluation metric's key.

Parameters
samples	a `fiftyone.core.collections.SampleCollection`
config	an `fiftyone.core.evaluation.EvaluationMethodConfig`
eval_key	an evaluation key
new_eval_key	a new evaluation key