# tf.contrib.layers.maxout

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/contrib/layers/python/layers/layers.py#L3103-L3147) |

Adds a maxout op from <https://arxiv.org/abs/1302.4389>

    tf.contrib.layers.maxout(
        inputs, num_units, axis=-1, scope=None
    )

"Maxout Networks" Ian J. Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron
Courville,
Yoshua Bengio

Usually the operation is performed in the filter/channel dimension. This can
also be
used after fully-connected layers to reduce number of features.

<br />

<br />

<br />

| ## Arguments ||
|---|---|
| `inputs` | Tensor input |
| `num_units` | Specifies how many features will remain after maxout in the `axis` dimension (usually channel). This must be a factor of number of features. |
| `axis` | The dimension where max pooling will be performed. Default is the last dimension. |
| `scope` | Optional scope for variable_scope. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A `Tensor` representing the results of the pooling operation. ||

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | if num_units is not multiple of number of features. |

<br />