tf.contrib.layers.group_norm

tf.contrib.layers.group_norm(
    inputs,
    groups=32,
    channels_axis=-1,
    reduction_axes=(-3, -2),
    center=True,
    scale=True,
    epsilon=1e-06,
    activation_fn=None,
    param_initializers=None,
    reuse=None,
    variables_collections=None,
    outputs_collections=None,
    trainable=True,
    scope=None
)

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

Functional interface for the group normalization layer.

Reference: https://arxiv.org/abs/1803.08494.

"Group Normalization", Yuxin Wu, Kaiming He

Args:

• inputs: A Tensor with at least 2 dimensions one which is channels. All shape dimensions must be fully defined.
• groups: Integer. Divide the channels into this number of groups over which normalization statistics are computed. This number must be commensurate with the number of channels in inputs.
• channels_axis: An integer. Specifies index of channels axis which will be broken into groups, each of which whose statistics will be computed across. Must be mutually exclusive with reduction_axes. Preferred usage is to specify negative integers to be agnostic as to whether a batch dimension is included.

• reduction_axes: Tuple of integers. Specifies dimensions over which statistics will be accumulated. Must be mutually exclusive with channels_axis. Statistics will not be accumulated across axes not specified in reduction_axes nor channel_axis. Preferred usage is to specify negative integers to be agnostic to whether a batch dimension is included.

  Some sample usage cases: NHWC format: channels_axis=-1, reduction_axes=[-3, -2] NCHW format: channels_axis=-3, reduction_axes=[-2, -1]

• center: If True, add offset of beta to normalized tensor. If False, beta is ignored.

• scale: If True, multiply by gamma. If False, gamma is not used. When the next layer is linear (also e.g. nn.relu), this can be disabled since the scaling can be done by the next layer.
• epsilon: Small float added to variance to avoid dividing by zero.
• activation_fn: Activation function, default set to None to skip it and maintain a linear activation.
• param_initializers: Optional initializers for beta, gamma, moving mean and moving variance.
• 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 collections for the variables.
• outputs_collections: Collections 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:

A Tensor representing the output of the operation.

Raises:

• ValueError: If the rank of inputs is undefined.
• ValueError: If rank or channels dimension of inputs is undefined.
• ValueError: If number of groups is not commensurate with number of channels.
• ValueError: If reduction_axes or channels_axis are out of bounds.
• ValueError: If reduction_axes are not mutually exclusive with channels_axis.