tf.keras.metrics.sparse_categorical_accuracy

TensorFlow 1 version View source on GitHub

Calculates how often predictions matches integer labels.

tf.keras.metrics.sparse_categorical_accuracy(
    y_true, y_pred
)

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

Args:

  • y_true: Integer ground truth values.
  • y_pred: The prediction values.

Returns:

Sparse categorical accuracy values.