Computes the mean Intersection-Over-Union metric
metric_mean_iou(..., num_classes, name = NULL, dtype = NULL)A (subclassed) Metric instance that can be passed directly to
compile(metrics = ), or used as a standalone object. See ?Metric for
example usage.
Passed on to the underlying metric. Used for forwards and backwards compatibility.
The possible number of labels the prediction task can have.
This value must be provided, since a confusion matrix of dim
c(num_classes, num_classes) will be allocated.
(Optional) string name of the metric instance.
(Optional) data type of the metric result.
Mean Intersection-Over-Union is a common evaluation metric for semantic image segmentation, which first computes the IOU for each semantic class and then computes the average over classes. IOU is defined as follows:
IOU = true_positive / (true_positive + false_positive + false_negative)
The predictions are accumulated in a confusion matrix, weighted by
sample_weight and the metric is then calculated from it.
If sample_weight is NULL, weights default to 1.
Use sample_weight of 0 to mask values.
Other metrics:
custom_metric(),
metric_accuracy(),
metric_auc(),
metric_binary_accuracy(),
metric_binary_crossentropy(),
metric_categorical_accuracy(),
metric_categorical_crossentropy(),
metric_categorical_hinge(),
metric_cosine_similarity(),
metric_false_negatives(),
metric_false_positives(),
metric_hinge(),
metric_kullback_leibler_divergence(),
metric_logcosh_error(),
metric_mean_absolute_error(),
metric_mean_absolute_percentage_error(),
metric_mean_relative_error(),
metric_mean_squared_error(),
metric_mean_squared_logarithmic_error(),
metric_mean_tensor(),
metric_mean_wrapper(),
metric_mean(),
metric_poisson(),
metric_precision_at_recall(),
metric_precision(),
metric_recall_at_precision(),
metric_recall(),
metric_root_mean_squared_error(),
metric_sensitivity_at_specificity(),
metric_sparse_categorical_accuracy(),
metric_sparse_categorical_crossentropy(),
metric_sparse_top_k_categorical_accuracy(),
metric_specificity_at_sensitivity(),
metric_squared_hinge(),
metric_sum(),
metric_top_k_categorical_accuracy(),
metric_true_negatives(),
metric_true_positives()