NN_max_pool2d()

void NN_max_pool2d	(	Tensor *	out,
		const Tensor *	in,
		const size_t *	kernel_size
	)

Applies a 2D max pooling over an input signal composed of several input planes.

Parameters

out	the output tensor of shape (batch_size, channels, height, width)
in	the input tensor of shape (batch_size, channels, pooled_height, pooled_width)
kernel_size	size of the pooling window