tf.keras.metrics.OneHotIoU

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

Inherits From: IoU, Metric

tf.keras.metrics.OneHotIoU(
    num_classes,
    target_class_ids,
    name=None,
    dtype=None,
    ignore_class=None,
    sparse_y_pred=False,
    axis=-1
)

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

This class can be used to compute 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 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 IoU class apply.

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

Args
num_classes	The possible number of labels the prediction task can have.
target_class_ids	A tuple or list of target class ids for which the metric is returned. To compute IoU for a specific class, a list (or tuple) of a single id value should be provided.
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_pred	Whether predictions are encoded using integers or dense floating point vectors. If False, the argmax function is used to determine each sample's most likely associated label.
axis	(Optional) The dimension containing the logits. Defaults to -1.

Example:

Example:

y_true = np.array([[0, 0, 1], [1, 0, 0], [0, 1, 0], [1, 0, 0]])
y_pred = np.array([[0.2, 0.3, 0.5], [0.1, 0.2, 0.7], [0.5, 0.3, 0.1],
                      [0.1, 0.4, 0.5]])
sample_weight = [0.1, 0.2, 0.3, 0.4]
m = keras.metrics.OneHotIoU(num_classes=3, target_class_ids=[0, 2])
m.update_state(
    y_true=y_true, y_pred=y_pred, sample_weight=sample_weight)
# cm = [[0, 0, 0.2+0.4],
#       [0.3, 0, 0],
#       [0, 0, 0.1]]
# sum_row = [0.3, 0, 0.7], sum_col = [0.6, 0.3, 0.1]
# true_positives = [0, 0, 0.1]
# single_iou = true_positives / (sum_row + sum_col - true_positives))
# mean_iou = (0 / (0.3 + 0.6 - 0) + 0.1 / (0.7 + 0.1 - 0.1)) / 2
m.result()
0.071

Usage with compile() API:

model.compile(
    optimizer='sgd',
    loss='mse',
    metrics=[keras.metrics.OneHotIoU(
        num_classes=3,
        target_class_id=[1]
    )]
)

Attributes
dtype
variables

Methods

add_variable

View source

add_variable(
    shape, initializer, dtype=None, aggregation='sum', name=None
)

add_weight

View source

add_weight(
    shape=(), initializer=None, dtype=None, name=None
)

from_config

View source

@classmethod
from_config(
    config
)

get_config

View source

get_config()

Return the serializable config of the metric.

reset_state

View source

reset_state()

Reset 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 intersection-over-union via the confusion matrix.

stateless_reset_state

View source

stateless_reset_state()

stateless_result

View source

stateless_result(
    metric_variables
)

stateless_update_state

View source

stateless_update_state(
    metric_variables, *args, **kwargs
)

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. Can be a Tensor whose rank is either 0, or the same as y_true, and must be broadcastable to y_true. Defaults to 1.

Returns
Update op.

__call__

View source

__call__(
    *args, **kwargs
)

Call self as a function.