tf.keras.metrics.MeanIoU

Computes the mean Intersection-Over-Union metric.

Inherits From: Metric, Layer, Module

tf.keras.metrics.MeanIoU(
    num_classes, name=None, dtype=None
)

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

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

reset_state

View source

reset_state()

Resets all of the metric state variables.

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

result

View source

result()

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

update_state

View source

update_state(
    y_true, y_pred, sample_weight=None
)

Accumulates the confusion matrix statistics.

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

Returns
Update op.