# tf.keras.losses.cosine_similarity

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.1.0/tensorflow/python/keras/losses.py#L1064-L1093) |

Computes the cosine similarity between labels and predictions.

#### View aliases


**Main aliases**

[`tf.losses.cosine_similarity`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/cosine_similarity)
**Compat aliases for migration**

See
[Migration guide](https://www.tensorflow.org/guide/migrate) for
more details.

[`tf.compat.v1.keras.losses.cosine`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/cosine_similarity), [`tf.compat.v1.keras.losses.cosine_proximity`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/cosine_similarity), [`tf.compat.v1.keras.losses.cosine_similarity`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/cosine_similarity), [`tf.compat.v1.keras.metrics.cosine`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/cosine_similarity), [`tf.compat.v1.keras.metrics.cosine_proximity`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/cosine_similarity)

<br />

    tf.keras.losses.cosine_similarity(
        y_true, y_pred, axis=-1
    )

Note that it is a negative quantity between -1 and 0, where 0 indicates
orthogonality and values closer to -1 indicate greater similarity. This makes
it usable as a loss function in a setting where you try to maximize the
proximity between predictions and targets.

`loss = -sum(y_true * y_pred)`

<br />

<br />

<br />

| ## Args ||
|---|---|
| `y_true` | Tensor of true targets. |
| `y_pred` | Tensor of predicted targets. |
| `axis` | Axis along which to determine similarity. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| Cosine similarity tensor. ||

<br />