Skip to contents

Computes mean Intersection-Over-Union metric for one-hot encoded labels.

Source: R/metrics.R
metric_one_hot_mean_iou.Rd

Formula:

iou <- true_positives / (true_positives + false_positives + false_negatives)

Intersection-Over-Union is a common evaluation metric for semantic image segmentation.

To compute IoUs, 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.

This class can be used to compute the mean IoU for multi-class classification tasks where the labels are one-hot encoded (the last axis should have one dimension per class). Note that the predictions should also have the same shape. To compute the mean IoU, first the labels and predictions are converted back into integer format by taking the argmax over the class axis. Then the same computation steps as for the base MeanIoU class apply.

Note, if there is only one channel in the labels and predictions, this class is the same as class metric_mean_iou. In this case, use metric_mean_iou instead.

Also, make sure that num_classes is equal to the number of classes in the data, to avoid a "labels out of bound" error when the confusion matrix is computed.

Usage

metric_one_hot_mean_iou(
  ...,
  num_classes,
  name = NULL,
  dtype = NULL,
  ignore_class = NULL,
  sparse_y_pred = FALSE,
  axis = -1L
)

Arguments

...

For forward/backward compatability.

num_classes

The possible number of labels the prediction task can have.

name

(Optional) string name of the metric instance.

dtype

(Optional) data type of the metric result.

ignore_class

Optional integer. The ID of a class to be ignored during metric computation. This is useful, for example, in segmentation problems featuring a "void" class (commonly -1 or 255) in segmentation maps. By default (ignore_class=NULL), all classes are considered.

sparse_y_pred

Whether predictions are encoded using natural numbers or probability distribution vectors. If FALSE, the argmax function will be used to determine each sample's most likely associated label.

axis

(Optional) The dimension containing the logits. Defaults to -1.

Value

a Metric instance is returned. The Metric instance can be passed directly to compile(metrics = ), or used as a standalone object. See ?Metric for example usage.

Examples

Standalone usage:

y_true <- rbind(c(0, 0, 1), c(1, 0, 0), c(0, 1, 0), c(1, 0, 0))
y_pred <- rbind(c(0.2, 0.3, 0.5), c(0.1, 0.2, 0.7), c(0.5, 0.3, 0.1),
                c(0.1, 0.4, 0.5))
sample_weight <- c(0.1, 0.2, 0.3, 0.4)
m <- metric_one_hot_mean_iou(num_classes = 3L)
m$update_state(
    y_true = y_true, y_pred = y_pred, sample_weight = sample_weight)
m$result()

## tf.Tensor(0.047619034, shape=(), dtype=float32)

Usage with compile() API:

model %>% compile(
    optimizer = 'sgd',
    loss = 'mse',
    metrics = list(metric_one_hot_mean_iou(num_classes = 3L)))

See also

Other iou metrics:
metric_binary_iou()
metric_iou()
metric_mean_iou()
metric_one_hot_iou()

Other metrics:
Metric()
custom_metric()
metric_auc()
metric_binary_accuracy()
metric_binary_crossentropy()
metric_binary_focal_crossentropy()
metric_binary_iou()
metric_categorical_accuracy()
metric_categorical_crossentropy()
metric_categorical_focal_crossentropy()
metric_categorical_hinge()
metric_cosine_similarity()
metric_f1_score()
metric_false_negatives()
metric_false_positives()
metric_fbeta_score()
metric_hinge()
metric_huber()
metric_iou()
metric_kl_divergence()
metric_log_cosh()
metric_log_cosh_error()
metric_mean()
metric_mean_absolute_error()
metric_mean_absolute_percentage_error()
metric_mean_iou()
metric_mean_squared_error()
metric_mean_squared_logarithmic_error()
metric_mean_wrapper()
metric_one_hot_iou()
metric_poisson()
metric_precision()
metric_precision_at_recall()
metric_r2_score()
metric_recall()
metric_recall_at_precision()
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()