Class BatchNorm

tensorlayer/layers/normalization.py:149–308

The :class:`BatchNorm` is a batch normalization layer for both fully-connected and convolution outputs. See ``tf.nn.batch_normalization`` and ``tf.nn.moments``. Parameters ---------- decay : float A decay factor for `ExponentialMovingAverage`. Suggest to use a l

class BatchNorm(Layer):
    """
    The :class:`BatchNorm` is a batch normalization layer for both fully-connected and convolution outputs.
    See ``tf.nn.batch_normalization`` and ``tf.nn.moments``.

    Parameters
    ----------
    decay : float
        A decay factor for `ExponentialMovingAverage`.
        Suggest to use a large value for large dataset.
    epsilon : float
        Eplison.
    act : activation function
        The activation function of this layer.
    is_train : boolean
        Is being used for training or inference.
    beta_init : initializer or None
        The initializer for initializing beta, if None, skip beta.
        Usually you should not skip beta unless you know what happened.
    gamma_init : initializer or None
        The initializer for initializing gamma, if None, skip gamma.
        When the batch normalization layer is use instead of 'biases', or the next layer is linear, this can be
        disabled since the scaling can be done by the next layer. see `Inception-ResNet-v2 <https://github.com/tensorflow/models/blob/master/research/slim/nets/inception_resnet_v2.py>`__
    moving_mean_init : initializer or None
        The initializer for initializing moving mean, if None, skip moving mean.
    moving_var_init : initializer or None
        The initializer for initializing moving var, if None, skip moving var.
    num_features: int
        Number of features for input tensor. Useful to build layer if using BatchNorm1d, BatchNorm2d or BatchNorm3d,
        but should be left as None if using BatchNorm. Default None.
    data_format : str
        channels_last 'channel_last' (default) or channels_first.
    name : None or str
        A unique layer name.

    Examples
    ---------
    With TensorLayer

    >>> net = tl.layers.Input([None, 50, 50, 32], name='input')
    >>> net = tl.layers.BatchNorm()(net)

    Notes
    -----
    The :class:`BatchNorm` is universally suitable for 3D/4D/5D input in static model, but should not be used
    in dynamic model where layer is built upon class initialization. So the argument 'num_features' should only be used
    for subclasses :class:`BatchNorm1d`, :class:`BatchNorm2d` and :class:`BatchNorm3d`. All the three subclasses are
    suitable under all kinds of conditions.

    References
    ----------
    - `Source <https://github.com/ry/tensorflow-resnet/blob/master/resnet.py>`__
    - `stackoverflow <http://stackoverflow.com/questions/38312668/how-does-one-do-inference-with-batch-normalization-with-tensor-flow>`__

    """

    def __init__(
        self,