# tf.keras.metrics.sparse_top_k_categorical_accuracy

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.14.0/keras/metrics/accuracy_metrics.py#L499-L527) |

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

#### View aliases


**Main aliases**

[`tf.metrics.sparse_top_k_categorical_accuracy`](https://www.tensorflow.org/api_docs/python/tf/keras/metrics/sparse_top_k_categorical_accuracy)

<br />

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

#### Standalone usage:

    y_true = [2, 1]
    y_pred = [[0.1, 0.9, 0.8], [0.05, 0.95, 0]]
    m = tf.keras.metrics.sparse_top_k_categorical_accuracy(
        y_true, y_pred, k=3)
    assert m.shape == (2,)
    m.numpy()
    array([1., 1.], dtype=float32)

<br />

<br />

<br />

| ## 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`. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| Sparse top K categorical accuracy value. ||

<br />