tf.nn.moments(x, axes, shift=None, name=None, keep_dims=False)
See the guide: Neural Network > Normalization
Calculate the mean and variance of
The mean and variance are calculated by aggregating the contents of
x is 1-D and
axes =  this is just the mean
and variance of a vector.
When using these moments for batch normalization (see
- for so-called "global normalization", used with convolutional filters with
[batch, height, width, depth], pass
axes=[0, 1, 2].
- for simple batch normalization pass
axes: Array of ints. Axes along which to compute mean and variance.
Tensorcontaining the value by which to shift the data for numerical stability, or
Nonein which case the true mean of the data is used as shift. A shift close to the true mean provides the most numerically stable results.
name: Name used to scope the operations that compute the moments.
keep_dims: produce moments with the same dimensionality as the input.