<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.21.0/tensorflow/python/ops/nn_ops.py#L3915-L3922) |

Computes softmax activations.

#### View aliases


**Compat aliases for migration**

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

[`tf.compat.v1.nn.softmax`](https://www.tensorflow.org/api_docs/python/tf/compat/v1/math/softmax)

<br />

    tf.compat.v1.math.softmax(
        logits, axis=None, name=None, dim=None
    )

### Used in the notebooks

| Used in the tutorials |
|---|
| - [Fitting Dirichlet Process Mixture Model Using Preconditioned Stochastic Gradient Langevin Dynamics](https://www.tensorflow.org/probability/examples/Fitting_DPMM_Using_pSGLD) |

Used for multi-class predictions. The sum of all outputs generated by softmax
is 1.

This function performs the equivalent of

    softmax = tf.exp(logits) / tf.reduce_sum(tf.exp(logits), axis, keepdims=True)

Example usage:

    softmax = tf.nn.softmax([-1, 0., 1.])
    softmax
    <tf.Tensor: shape=(3,), dtype=float32,
    numpy=array([0.09003057, 0.24472848, 0.66524094], dtype=float32)>
    sum(softmax)
    <tf.Tensor: shape=(), dtype=float32, numpy=1.0>

<br />

<br />

<br />

| ## Args ||
|---|---|
| `logits` | A non-empty `Tensor`. Must be one of the following types: `half`, `float32`, `float64`. |
| `axis` | The dimension softmax would be performed on. The default is -1 which indicates the last dimension. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A `Tensor`. Has the same type and shape as `logits`. ||

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `InvalidArgumentError` | if `logits` is empty or `axis` is beyond the last dimension of `logits`. |

<br />