# tf.contrib.layers.legacy_fully_connected

|---|
| [![](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#L3187-L3317) |

Adds the parameters for a fully connected layer and returns the output.

    tf.contrib.layers.legacy_fully_connected(
        x, num_output_units, activation_fn=None,
        weight_init=initializers.xavier_initializer(), bias_init=tf.zeros_initializer(),
        name=None, weight_collections=(ops.GraphKeys.WEIGHTS,),
        bias_collections=(ops.GraphKeys.BIASES,),
        output_collections=(ops.GraphKeys.ACTIVATIONS,), trainable=True,
        weight_regularizer=None, bias_regularizer=None
    )

A fully connected layer is generally defined as a matrix multiply:
`y = f(w * x + b)` where `f` is given by `activation_fn`. If
`activation_fn` is `None`, the result of `y = w * x + b` is
returned.

If `x` has shape \[\\(\\text{dim}_0, \\text{dim}_1, ..., \\text{dim}_n\\)\]
with more than 2 dimensions (\\(n \> 1\\)), then we repeat the matrix
multiply along the first dimensions. The result r is a tensor of shape
\[\\(\\text{dim}_0, ..., \\text{dim}_{n-1},\\) `num_output_units`\],
where \\( r_{i_0, ..., i_{n-1}, k} =
\\sum_{0 \\leq j \< \\text{dim}_n} x_{i_0, ... i_{n-1}, j} \\cdot w_{j, k}\\).
This is accomplished by reshaping `x` to 2-D
\[\\(\\text{dim}_0 \\cdot ... \\cdot \\text{dim}_{n-1}, \\text{dim}_n\\)\]
before the matrix multiply and afterwards reshaping it to
\[\\(\\text{dim}_0, ..., \\text{dim}_{n-1},\\) `num_output_units`\].

This op creates `w` and optionally `b`. Bias (`b`) can be disabled by setting
`bias_init` to `None`.

The variable creation is compatible with [`tf.compat.v1.variable_scope`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/variable_scope) and so
can be
reused with [`tf.compat.v1.variable_scope`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/variable_scope) or [`tf.compat.v1.make_template`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/make_template).

Most of the details of variable creation can be controlled by specifying the
initializers (`weight_init` and `bias_init`) and in which collections to place
the created variables (`weight_collections` and `bias_collections`; note that
the variables are always added to the `VARIABLES` collection). The output of
the layer can be placed in custom collections using `output_collections`.
The collections arguments default to `WEIGHTS`, `BIASES` and `ACTIVATIONS`,
respectively.

A per layer regularization can be specified by setting `weight_regularizer`
and `bias_regularizer`, which are applied to the weights and biases
respectively, and whose output is added to the `REGULARIZATION_LOSSES`
collection.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `x` | The input `Tensor`. |
| `num_output_units` | The size of the output. |
| `activation_fn` | Activation function, default set to None to skip it and maintain a linear activation. |
| `weight_init` | An optional weight initialization, defaults to `xavier_initializer`. |
| `bias_init` | An initializer for the bias, defaults to 0. Set to `None` in order to disable bias. |
| `name` | The name for this operation is used to name operations and to find variables. If specified it must be unique for this scope, otherwise a unique name starting with "fully_connected" will be created. See [`tf.compat.v1.variable_scope`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/variable_scope) for details. |
| `weight_collections` | List of graph collections to which weights are added. |
| `bias_collections` | List of graph collections to which biases are added. |
| `output_collections` | List of graph collections to which outputs are added. |
| `trainable` | If `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see tf.Variable). |
| `weight_regularizer` | A regularizer like the result of `l1_regularizer` or `l2_regularizer`. Used for weights. |
| `bias_regularizer` | A regularizer like the result of `l1_regularizer` or `l2_regularizer`. Used for biases. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| The output of the fully connected layer. ||

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | If x has rank less than 2 or if its last dimension is not set. |

<br />