# tf.keras.activations.softmax

<br />

|---|---|
| [![](https://www.tensorflow.org/images/tf_logo_32px.png) TensorFlow 1 version](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/keras/activations/softmax) | [![](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/activations.py#L43-L79) |

Softmax converts a real vector to a vector of categorical probabilities.

#### View aliases


**Compat aliases for migration**

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

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

<br />

    tf.keras.activations.softmax(
        x, axis=-1
    )

The the elements of the output vector are in range (0, 1) and sum to 1.

Each vector is handled independently. The `axis` argument sets which axis
of the input the finction is applied along.

Softmax is often used as the activation for the last
layer of a classification network because the result could be interpreted as
a probability distribution.

The softmax of each vector x is calculated by `exp(x)/tf.reduce_sum(exp(x))`.
The input values in are the log-odds of the resulting probability.

<br />

<br />

<br />

| ## Arguments ||
|---|---|
| `x` | Input tensor. |
| `axis` | Integer, axis along which the softmax normalization is applied. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| Tensor, output of softmax transformation (all values are non-negative and sum to 1). ||

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | In case `dim(x) == 1`. |

<br />