chainer.functions.average_pooling_nd(x, ksize, stride=None, pad=0, pad_value=0)[source]

N-dimensionally spatial average pooling function.


This feature is experimental. The interface can change in the future.

This function provides a N-dimensionally generalized version of average_pooling_2d(). This acts similarly to convolution_nd(), but it computes the average of input spatial patch for each channel without any parameter instead of computing the inner products.

  • x (Variable) – Input variable.
  • ksize (int or tuple of ints) – Size of pooling window. ksize=k and ksize=(k, k, ..., k) are equivalent.
  • stride (int or tuple of ints or None) – Stride of pooling applications. stride=s and stride=(s, s, ..., s) are equivalent. If None is specified, then it uses same stride as the pooling window size.
  • pad (int or tuple of ints) – Spatial padding width for the input array. pad=p and pad=(p, p, ..., p) are equivalent.
  • pad_value (0 or None) – Value to fill the padded region when calculating average. If None is specified, such region is ignored. The default value is 0, therefore the averages are biased towards zero.

Output variable.

Return type:



This function currently does not support cover_all mode as max_pooling_nd(). Average pooling runs in non-cover-all mode.