AdaptiveAvgPool2d¶

class AdaptiveAvgPool2d(oshp, **kwargs)[源代码]¶

对输入数据进行2D平均池化。

例如，给定形状为 $(N, C, H, W)$ 的输入以及形为 $(k H, k W)$ 的 kernel_size, 该层产生形状为 $(N, C, H_{o u t}, W_{o u t})$ 的输出。生成过程描述如下：

o u t (N_{i}, C_{j}, h, w) = \frac{1}{k H * k W} \sum_{m = 0}^{k H - 1} \sum_{n = 0}^{k W - 1} i n p u t (N_{i}, C_{j}, s t r i d e [0] \times h + m, s t r i d e [1] \times w + n)

kernel_size and stride can be inferred from input shape and out shape:

padding: (0, 0)
stride: (floor(IH / OH), floor(IW / OW))
kernel_size: (IH - (OH - 1) * stride_h, IW - (OW - 1) * stride_w)

实际案例

import numpy as np
import megengine as mge
import megengine.module as M

m = M.AdaptiveAvgPool2d((2, 2))
inp = mge.tensor(np.arange(0, 16).astype("float32").reshape(1, 1, 4, 4))
oup = m(inp)
print(oup.numpy())

输出：

[[[[ 2.5  4.5]
   [10.5 12.5]]]]

MaxPool2d

AdaptiveMaxPool2d