TensorFlow 2 version View source on GitHub

Calculates how often predictions matches labels.

For example, if y_true is [[0, 0, 1], [0, 1, 0]] and y_pred is [[0.1, 0.9, 0.8], [0.05, 0.95, 0]] then the categorical accuracy is 1/2 or .5. If the weights were specified as [0.7, 0.3] then the categorical accuracy would be .3. 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 tf.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.


m = tf.keras.metrics.CategoricalAccuracy()
m.update_state([[0, 0, 1], [0, 1, 0]], [[0.1, 0.9, 0.8], [0.05, 0.95, 0]])
print('Final result: ', m.result().numpy())  # Final result: 0.5

Usage with tf.keras API:

model = tf.keras.Model(inputs, outputs)

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



View source

Resets all of the metric state variables.

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


View source

Computes and returns the metric value tensor.

Result computation is an idempotent operation that simply calculates the metric value using the state variables.


View source

Accumulates metric statistics.

y_true and y_pred should have the same shape.

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.

Update op.