tensorflow Method源码阅读之 fully_connected

https://www.tensorflow.org/api_docs/python/tf/contrib/layers/fully_connected

fully_connected：

1、先根据权重得到输出

2、对输出normalizer (BN..)

3、对输出activate（relu, ...）

Defined in tensorflow/contrib/layers/python/layers/layers.py.

def fully_connected(inputs,
                    num_outputs,
                    activation_fn=nn.relu,
                    normalizer_fn=None,
                    normalizer_params=None,
                    weights_initializer=initializers.xavier_initializer(),
                    weights_regularizer=None,
                    biases_initializer=init_ops.zeros_initializer(),
                    biases_regularizer=None,
                    reuse=None,
                    variables_collections=None,
                    outputs_collections=None,
                    trainable=True,
                    scope=None):
  """Adds a fully connected layer.

  `fully_connected` creates a variable called `weights`, representing a fully
  connected weight matrix, which is multiplied by the `inputs` to produce a
  `Tensor` of hidden units. If a `normalizer_fn` is provided (such as
  `batch_norm`), it is then applied. Otherwise, if `normalizer_fn` is
  None and a `biases_initializer` is provided then a `biases` variable would be
  created and added the hidden units. Finally, if `activation_fn` is not `None`,
  it is applied to the hidden units as well.

  Note: that if `inputs` have a rank greater than 2, then `inputs` is flattened
  prior to the initial matrix multiply by `weights`.

  Args:
    inputs: A tensor of at least rank 2 and static value for the last dimension;
      i.e. `[batch_size, depth]`, `[None, None, None, channels]`.
    num_outputs: Integer or long, the number of output units in the layer.
    activation_fn: Activation function. The default value is a ReLU function.
      Explicitly set it to None to skip it and maintain a linear activation.
    normalizer_fn: Normalization function to use instead of `biases`. If
      `normalizer_fn` is provided then `biases_initializer` and
      `biases_regularizer` are ignored and `biases` are not created nor added.
      default set to None for no normalizer function
    normalizer_params: Normalization function parameters.
    weights_initializer: An initializer for the weights.
    weights_regularizer: Optional regularizer for the weights.
    biases_initializer: An initializer for the biases. If None skip biases.
    biases_regularizer: Optional regularizer for the biases.
    reuse: Whether or not the layer and its variables should be reused. To be
      able to reuse the layer scope must be given.
    variables_collections: Optional list of collections for all the variables or
      a dictionary containing a different list of collections per variable.
    outputs_collections: Collection to add the outputs.
    trainable: If `True` also add variables to the graph collection
      `GraphKeys.TRAINABLE_VARIABLES` (see tf.Variable).
    scope: Optional scope for variable_scope.

  Returns:
     The tensor variable representing the result of the series of operations.

  Raises:
    ValueError: If x has rank less than 2 or if its last dimension is not set.
  """
  if not isinstance(num_outputs, six.integer_types):
    raise ValueError('num_outputs should be int or long, got %s.' %
                     (num_outputs,))

  layer_variable_getter = _build_variable_getter({
      'bias': 'biases',
      'kernel': 'weights'
  })

  with variable_scope.variable_scope(
      scope,
      'fully_connected', [inputs],
      reuse=reuse,
      custom_getter=layer_variable_getter) as sc:
    inputs = ops.convert_to_tensor(inputs)
    layer = core_layers.Dense(
        units=num_outputs,
        activation=None,
        use_bias=not normalizer_fn and biases_initializer,
        kernel_initializer=weights_initializer,
        bias_initializer=biases_initializer,
        kernel_regularizer=weights_regularizer,
        bias_regularizer=biases_regularizer,
        activity_regularizer=None,
        trainable=trainable,
        name=sc.name,
        dtype=inputs.dtype.base_dtype,
        _scope=sc,
        _reuse=reuse)
    outputs = layer.apply(inputs)

    # Add variables to collections.
    _add_variable_to_collections(layer.kernel, variables_collections, 'weights')
    if layer.bias is not None:
      _add_variable_to_collections(layer.bias, variables_collections, 'biases')

    # Apply normalizer function / layer.
    if normalizer_fn is not None:
      if not normalizer_params:
        normalizer_params = {}
      outputs = normalizer_fn(outputs, **normalizer_params)

    if activation_fn is not None:
      outputs = activation_fn(outputs)

    return utils.collect_named_outputs(outputs_collections, sc.name, outputs)