AdaptiveMaxPool2d¶

class AdaptiveMaxPool2d(oshp, **kwargs)[source]¶

Applies a 2D max adaptive pooling over an input.

For instance, given an input of the size \((N, C, H, W)\) and an output shape \((OH, OW)\), this layer generates the output of the size \((N, C, OH, OW)\) through a process described as:

\[\begin{aligned} out(N_i, C_j, h, w) ={} & \max_{m=0, \ldots, kH-1} \max_{n=0, \ldots, kW-1} \text{input}(N_i, C_j, \text{stride[0]} \times h + m, \text{stride[1]} \times w + n) \end{aligned}\]

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)

Parameters: oshp (Union[Tuple[int, int], int, Tensor]) – the target output shape of the image of the form Height * Width. Can be tuple (H, W) or a single H for a square image H * H.

Shape:

Input: \((N, C, H_{in}, W_{in})\) or \((C, H_{in}, W_{in})\).
Output: \((N, C, H_{out}, W_{out})\) or \((C, H_{out}, W_{out})\), where \((H_{out}, W_{out})=\text{output\_shape}\).

Returns: module. The instance of the AdaptiveMaxPool2d module.
Return type: Return type

Examples

>>> import numpy as np
>>> m = M.AdaptiveMaxPool2d((2, 2))
>>> inp = mge.tensor(np.arange(0, 16).astype("float32").reshape(1, 1, 4, 4))
>>> oup = m(inp)
>>> oup.numpy()
array([[[[ 5.,  7.],
         [13., 15.]]]], dtype=float32)

AdaptiveAvgPool2d

DeformablePSROIPooling