TensorFlow 1 version View source on GitHub

Applies batch normalization on x given mean, var, beta and gamma.

    x, mean, var, beta, gamma, axis=-1, epsilon=0.001

I.e. returns: output = (x - mean) / (sqrt(var) + epsilon) * gamma + beta


  • x: Input tensor or variable.
  • mean: Mean of batch.
  • var: Variance of batch.
  • beta: Tensor with which to center the input.
  • gamma: Tensor by which to scale the input.
  • axis: Integer, the axis that should be normalized. (typically the features axis).
  • epsilon: Fuzz factor.


A tensor.