Table Of Contents
Table Of Contents



Batch normalization.

This operator is DEPRECATED. Perform BatchNorm on the input.

Normalizes a data batch by mean and variance, and applies a scale gamma as well as offset beta.

Assume the input has more than one dimension and we normalize along axis 1. We first compute the mean and variance along this axis:

\[\begin{split} data\_mean[i] = mean(data[:,i,:,...]) \\ data\_var[i] = var(data[:,i,:,...])\end{split}\]

Then compute the normalized output, which has the same shape as input, as following:

\[out[:,i,:,...] = \frac{data[:,i,:,...] - data\_mean[i]}{\sqrt{data\_var[i]+\epsilon}} * gamma[i] + beta[i]\]

Both mean and var returns a scalar by treating the input as a vector.

Assume the input has size k on axis 1, then both gamma and beta have shape (k,). If output_mean_var is set to be true, then outputs both data_mean and data_var as well, which are needed for the backward pass.

Besides the inputs and the outputs, this operator accepts two auxiliary states, moving_mean and moving_var, which are k-length vectors. They are global statistics for the whole dataset, which are updated by:

moving_mean = moving_mean * momentum + data_mean * (1 - momentum)
moving_var = moving_var * momentum + data_var * (1 - momentum)

If ``use_global_stats`` is set to be true, then ``moving_mean`` and
``moving_var`` are used instead of ``data_mean`` and ``data_var`` to compute
the output. It is often used during inference.

Both ``gamma`` and ``beta`` are learnable parameters. But if ``fix_gamma`` is true,
then set ``gamma`` to 1 and its gradient to 0.

There's no sparse support for this operator, and it will exhibit problematic behavior if used with
sparse tensors.






Input data to batch normalization


NDArray-or-Symbol gamma array


NDArray-or-Symbol beta array


float, optional, default=0.001.

Epsilon to prevent div 0


float, optional, default=0.9.

Momentum for moving average


boolean, optional, default=1.

Fix gamma while training

boolean, optional, default=0.

Whether use global moving statistics instead of local batch-norm. This will force change batch-norm into a scale shift operator.


boolean, optional, default=0.

Output All,normal mean and var