Skip to content


2D average pooling.

Average pooling operation for spatial data.


  • pool_size : Integer or 2 integers, factors by witch to downscale (vertical, horizontal). If only one integer is specified, the same window length will be used for boths dimensions. Default value is 2.
  • strides : Integer or array of 2 integers, stride values. If only one integer is specified, the smae window lenghth will be used for both dimensions. Default is 2.
  • padding : String, padding mode.
    'same_upper' and 'valid' are compatible with 'same' and 'valid' on Keras (TensorFlow).
    'general' is compatible with Caffe.
    The default is 'valid'.
  • pads : Integer(s), pad values to the input.
    Four integers mean [pad_top, pad_left, pad_bottom, pad_right].
    Two integers mean [pad_top, pad_left] where pad_bottom and pad_right are same as pad_top and pad_left respectively.
    One integer means that pad_top, pad_left, pad_bottom and pad_right have the same value.
    The default is 0.