chainer.functions.average

chainer.functions.average(x, axis=None, weights=None, keepdims=False)[source]

Calculate weighted average of array elements over a given axis.

Parameters
  • x (Variable or N-dimensional array) – Elements to sum.

  • axis (None or int or tuple of int) – Axis which the method is performed. With the default (axis = None) it performs a mean over all the dimensions of the input array.

  • weights (None or Variable or N-dimensional array) – An array holding weights to calculate weighted average. If it is None, all weights are assumed to be one. When axis is None, weights must have the same shape of x. And when axis is int, it must be 1-D array satisfing weights.shape == (x.shape[axis],).

  • keepdims (bool) – If True, the specified axes are remained as axes of length one.

Returns

Output variable.

Return type

Variable