# chainerx.max_pool¶

chainerx.max_pool(x, ksize, stride=None, pad=0, cover_all=False)

Spatial max pooling function.

This acts similarly to conv(), but it computes the maximum of input spatial patch for each channel without any parameter instead of computing the inner products.

Parameters
• x (ndarray) – Input array.

• 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.

• cover_all (bool) – If True, all spatial locations are pooled into some output pixels. It may make the output size larger.

Returns

Output array.

Return type

ndarray

Note

During backpropagation, this function propagates the gradient of the output array to the input array x. This function is only differentiable up to the second order.

Note

In cuda backend, only 2 and 3 dim arrays are supported as x because cuDNN pooling supports 2 and 3 spatial dimensions.