chainerx.fixed_batch_norm

chainerx.fixed_batch_norm(x, gamma, beta, mean, var, eps=2e-05, axis=None)

Batch normalization function with fixed statistics.

This is a variant of batch_norm(), where the mean and array statistics are given by the caller as fixed variables.

Parameters
  • x (ndarray) – Input array.

  • gamma (ndarray) – Scaling parameter of normalized data.

  • beta (ndarray) – Shifting parameter of scaled normalized data.

  • mean (ndarray) – Shifting parameter of input.

  • var (ndarray) – Square of scaling parameter of input.

  • eps (float) – Epsilon value for numerical stability.

  • axis (int, tuple of int or None) – Axis over which normalization is performed. When axis is None, the first axis is treated as the batch axis and will be reduced during normalization.

Note

During backpropagation, this function does not propagate gradients.