tf.keras.metrics.sparse_top_k_categorical_accuracy

TensorFlow 1 version View source on GitHub

Computes how often integer targets are in the top K predictions.

tf.keras.metrics.sparse_top_k_categorical_accuracy(
    y_true, y_pred, k=5
)

Args:

  • y_true: tensor of true targets.
  • y_pred: tensor of predicted targets.
  • k: (Optional) Number of top elements to look at for computing accuracy. Defaults to 5.

Returns:

Sparse top K categorical accuracy value.