trw.train.metrics
¶
Module Contents¶
Classes¶
A metric base class |
|
Extract the loss from the outputs |
|
Calculate the accuracy using the output_truth and output |
|
Calculate the sensitivity and specificity for a binary classification using the output_truth and output |
Functions¶
" |
|
" |
|
" |
- class trw.train.metrics.Metric¶
A metric base class
Calculate interesting metric
- __call__(self, outputs)¶
Calculate a metric from the outputs :param outputs: the data required to calculate the metric from :return: a tuple (metric name, metric value) or None
- class trw.train.metrics.MetricLoss¶
Bases:
Metric
Extract the loss from the outputs
- __call__(self, outputs)¶
Calculate a metric from the outputs :param outputs: the data required to calculate the metric from :return: a tuple (metric name, metric value) or None
- class trw.train.metrics.MetricClassificationError¶
Bases:
Metric
Calculate the accuracy using the output_truth and output
- __call__(self, outputs)¶
Calculate a metric from the outputs :param outputs: the data required to calculate the metric from :return: a tuple (metric name, metric value) or None
- class trw.train.metrics.MetricClassificationSensitivitySpecificity¶
Bases:
Metric
Calculate the sensitivity and specificity for a binary classification using the output_truth and output
- __call__(self, outputs)¶
Calculate a metric from the outputs :param outputs: the data required to calculate the metric from :return: a tuple (metric name, metric value) or None
- trw.train.metrics.default_classification_metrics()¶
” Default list of metrics used for classification
- trw.train.metrics.default_regression_metrics()¶
” Default list of metrics used for classification
- trw.train.metrics.default_segmentation_metrics()¶
” Default list of metrics used for classification