ClassifierMetric

Inheritance Diagram

Inheritance diagram of ashpy.metrics.classifier.ClassifierMetric

class ashpy.metrics.classifier.ClassifierMetric(metric, model_selection_operator=None, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/v0.2.0/docs/source/log', processing_predictions=None)[source]

Bases: ashpy.metrics.metric.Metric

Wrap a metric using argmax to extract predictions out of a classifier’s output.

Methods

__init__(metric[, model_selection_operator, …])

Initialize the Metric.

update_state(context)

Update the internal state of the metric, using the information from the context object.

Attributes

best_folder

Retrieve the folder used to save the best model when doing model selection.

best_model_sel_file

Retrieve the path to JSON file containing the measured performance of the best model.

logdir

Retrieve the log directory.

metric

Retrieve the tf.keras.metrics.Metric object.

model_selection_operator

Retrieve the operator used for model selection.

name

Retrieve the metric name.

__init__(metric, model_selection_operator=None, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/v0.2.0/docs/source/log', processing_predictions=None)[source]

Initialize the Metric.

Parameters
  • metric (tf.keras.metrics.Metric) – The Keras Metric to use with the classifier (e.g.: Accuracy()).

  • model_selection_operator (typing.Callable) –

    The operation that will be used when model_selection is triggered to compare the metrics, used by the update_state. Any typing.Callable behaving like an operator is accepted.

    Note

    Model selection is done ONLY if an model_selection_operator is specified here.

  • logdir (str) – Path to the log dir, defaults to a log folder in the current directory.

  • processing_predictions (typing.Dict) – A dict in the form of {“fn”: tf.argmax, “kwargs”: {“axis”: -1}} with a function “fn” to be used for predictions processing purposes and its “kwargs” as its keyword-arguments. Defaults to {“fn”: tf.argmax, “kwargs”: {“axis”: -1}}.

Return type

None

update_state(context)[source]

Update the internal state of the metric, using the information from the context object.

Parameters

context (ashpy.contexts.ClassifierContext) – An AshPy Context holding all the information the Metric needs.

Return type

None