tf.keras.metrics.CategoricalAccuracy

Calculates how often predictions match one-hot labels.

Inherits From: MeanMetricWrapper, Mean, Metric

You can provide logits of classes as y_pred, since argmax of logits and probabilities are same.

This metric creates two local variables, total and count that are used to compute the frequency with which y_pred matches y_true. This frequency is ultimately returned as categorical accuracy: an idempotent operation that simply divides total by count.

y_pred and y_true should be passed in as vectors of probabilities, rather than as labels. If necessary, use ops.one_hot to expand y_true as a vector.

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

name (Optional) string name of the metric instance.
dtype (Optional) data type of the metric result.

Standalone usage:

m = keras.metrics.CategoricalAccuracy()
m.update_state([[0, 0, 1], [0, 1, 0]], [[0.1, 0.9, 0.8],
                [0.05, 0.95, 0]])
m.result()
0.5
m.reset_state()
m.update_state([[0, 0, 1], [0, 1, 0]], [[0.1, 0.9, 0.8],
                [0.05, 0.95, 0]],
               sample_weight=[0.7, 0.3])
m.result()
0.3

Usage with compile() API:

model.compile(optimizer='sgd',
              loss='categorical_crossentropy',
              metrics=[keras.metrics.CategoricalAccuracy()])

dtype

variables

Methods

add_variable

View source

add_weight

View source

from_config

View source

get_config

View source

Return the serializable config of the metric.

reset_state

View source

Reset 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 current metric value.

Returns
A scalar tensor, or a dictionary of scalar tensors.

stateless_reset_state

View source

stateless_result

View source

stateless_update_state

View source

update_state

View source

Accumulate statistics for the metric.

__call__

View source

Call self as a function.