tf.keras.metrics.sparse_categorical_accuracy

Calculates how often predictions match integer labels.

Standalone usage:

y_true = [2, 1]
y_pred = [[0.1, 0.9, 0.8], [0.05, 0.95, 0]]
m = tf.keras.metrics.sparse_categorical_accuracy(y_true, y_pred)
assert m.shape == (2,)
m.numpy()
array([0., 1.], dtype=float32)

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

y_true Integer ground truth values.
y_pred The prediction values.

Sparse categorical accuracy values.