View source on GitHub |
Computes the Intersection-Over-Union metric for class 0 and/or 1.
Inherits From: IoU
, Metric
, Layer
, Module
tf.keras.metrics.BinaryIoU(
target_class_ids: Union[List[int], Tuple[int, ...]] = (0, 1),
threshold=0.5,
name=None,
dtype=None
)
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.
This class can be used to compute IoUs for a binary classification task where
the predictions are provided as logits. First a threshold
is applied to the
predicted values such that those that are below the threshold
are converted
to class 0 and those that are above the threshold
are converted to class 1.
IoUs for classes 0 and 1 are then computed, the mean of IoUs for the classes
that are specified by target_class_ids
is returned.
Standalone usage:
m = tf.keras.metrics.BinaryIoU(target_class_id=[0, 1], threshold=0.3)
m.update_state([0, 1, 0, 1], [0.1, 0.2, 0.4, 0.7])
m.result().numpy()
0.33333334
m.reset_state()
m.update_state([0, 1, 0, 1], [0.1, 0.2, 0.4, 0.7],
sample_weight=[0.2, 0.3, 0.4, 0.1])
# cm = [[0.2, 0.4],
# [0.3, 0.1]]
# sum_row = [0.6, 0.4], sum_col = [0.5, 0.5], true_positives = [0.2, 0.1]
# iou = [0.222, 0.125]
m.result().numpy()
0.17
Usage with compile()
API:
model.compile(
optimizer='sgd',
loss='mse',
metrics=[tf.keras.metrics.BinaryIoU(target_class_id=[0], threshold=0.5)])
Methods
merge_state
merge_state(
metrics
)
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
reset_state()
Resets all of the metric state variables.
This function is called between epochs/steps, when a metric is evaluated during training.
result
result()
Compute the intersection-over-union via the confusion matrix.
update_state
update_state(
y_true, y_pred, sample_weight=None
)
Accumulates the confusion matrix statistics.
Before the confusion matrix is updated, the predicted values are thresholded
to be:
0 for values that are smaller than the threshold
1 for values that are larger or equal to the threshold
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. |