avgpool2d

Builtin index · Statistics & ML

result = avgpool2d(x, size, [stride=])

Input: x, size, stride · Output: result

What it is

Downsamples an (H, W) matrix x the same way as maxpool2d — size x size windows, stride defaulting to size — but takes the mean of each window instead of the max.

Overloads

One call shape — this function is not overloaded.

Examples

From the documentation, and run by the build -- the output and the figure below are what the engine actually produced. Simplest first.

x1d = [1.0, 2.0, 3.0, 4.0, 5.0]
edge_kernel = [1.0, 0.0, -1.0]
y1d = conv1d(x1d, edge_kernel)
print("conv1d edge response: {y1d}")

img = [1, 5, 2, 8; 4, 3, 9, 1; 7, 2, 6, 0; 1, 1, 1, 1]
k2d = [1, 0; 0, -1]
y2d = conv2d(img, k2d, 1, "valid")
print("conv2d output:\n{y2d}")

print("maxpool2d: {maxpool2d(img, 2)}")
print("avgpool2d: {avgpool2d(img, 2)}")

conv1d edge response: [-2, -2, -2]
conv2d output:
[-2, -4, 1; 2, -3, 9; 6, 1, 5]
maxpool2d: [5, 9; 7, 6]
avgpool2d: [3.25, 5; 2.75, 2]

from statistics-ml

How it works

avgpool2d(x, pool_size, [stride]) — 2-D average pooling, "valid" only, stride defaulting to pool_size the same way maxpool2d does. Backward divides each upstream gradient element evenly across its whole pooling window.

From the note above this builtin in the interpreter, where the reasoning was written down as it was built.