tf.keras.metrics.MeanIoU

Computes the mean Intersection-Over-Union metric.

Inherits From: IoU, Metric, Layer, Module

General definition and computation:

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

For an individual class, the IoU metric is defined as follows:

iou = true_positives / (true_positives + false_positives + false_negatives)

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 None, weights default to 1. Use sample_weight of 0 to mask values.

Note that this class first computes IoUs for all individual classes, then returns the mean of these values.

num_classes The possible number of labels the prediction task can have. This value must be provided, since a confusion matrix of dimension = [num_classes, num_classes] will be allocated.
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=None), all classes are considered.
sparse_y_true Whether labels are encoded using integers or dense floating point vectors. If False, the tf.argmax function will be used to determine each sample's most likely associated label.
sparse_y_pred Whether predictions are encoded using integers or dense floating point vectors. If False, the tf.argmax function will be used to determine each sample's most likely associated label.
axis (Optional) The dimension containing the logits. Defaults to -1.

Standalone usage:

# cm = [[1, 1],
#        [1, 1]]
# sum_row = [2, 2], sum_col = [2, 2], true_positives = [1, 1]
# iou = true_positives / (sum_row + sum_col - true_positives))
# result = (1 / (2 + 2 - 1) + 1 / (2 + 2 - 1)) / 2 = 0.33
m = tf.keras.metrics.MeanIoU(num_classes=2)
m.update_state([0, 0, 1, 1], [0, 1, 0, 1])
m.result().numpy()
0.33333334
m.reset_state()
m.update_state([0, 0, 1, 1], [0, 1, 0, 1],
               sample_weight=[0.3, 0.3, 0.3, 0.1])
m.result().numpy()
0.23809525

Usage with compile() API:

model.compile(
  optimizer='sgd',
  loss='mse',
  metrics=[tf.keras.metrics.MeanIoU(num_classes=2)])

Methods

merge_state

View source

Merges the state from one or more metrics.

This method can be used by distributed systems to merge the state computed by different metric instances. Typically the state will be stored in the form of the metric's weights. For example, a tf.keras.metrics.Mean metric contains a list of two weight values: a total and a count. If there were two instances of a tf.keras.metrics.Accuracy that each independently aggregated partial state for an overall accuracy calculation, these two metric's states could be combined as follows:

m1 = tf.keras.metrics.Accuracy()
_ = m1.update_state([[1], [2]], [[0], [2]])
m2 = tf.keras.metrics.Accuracy()
_ = m2.update_state([[3], [4]], [[3], [4]])
m2.merge_state([m1])
m2.result().numpy()
0.75

Args
metrics an iterable of metrics. The metrics must have compatible state.

Raises
ValueError If the provided iterable does not contain metrics matching the metric's required specifications.

reset_state

View source

Resets all of the metric state variables.

This function is called between epochs/steps, when a metric is evaluated during training.

result

View source

Compute the intersection-over-union via the confusion matrix.

update_state

View source

Accumulates the confusion matrix statistics.

Args
y_true The ground truth values.
y_pred The predicted values.
sample_weight Optional weighting of each example. Can be a Tensor whose rank is either 0, or the same rank as y_true, and must be broadcastable to y_true. Defaults to 1.

Returns
Update op.