AdaptiveMaxPool3D

class paddle.nn. AdaptiveMaxPool3D ( output_size, return_mask=False, name=None ) [source]

This operation applies 3D adaptive max pooling on input tensor. The h and w dimensions of the output tensor are determined by the parameter output_size. The difference between adaptive pooling and pooling is adaptive one focus on the output size.

For adaptive max pool3d:

\[ \begin{align}\begin{aligned}dstart &= floor(i * D_{in} / D_{out})\\dend &= ceil((i + 1) * D_{in} / D_{out})\\hstart &= floor(j * H_{in} / H_{out})\\hend &= ceil((j + 1) * H_{in} / H_{out})\\wstart &= floor(k * W_{in} / W_{out})\\wend &= ceil((k + 1) * W_{in} / W_{out})\\Output(i ,j, k) &= max(Input[dstart:dend, hstart:hend, wstart:wend])\end{aligned}\end{align} \]
Parameters
  • output_size (int|list|tuple) – The pool kernel size. If pool kernel size is a tuple or list, it must contain three elements, (D, H, W). D, H and W can be either a int, or None which means the size will be the same as that of the input.

  • return_mask (bool, optional) – If true, the index of max pooling point will be returned along with outputs. Default False.

  • name (str, optional) – For detailed information, please refer to Name. Usually name is no need to set and None by default.

Shape:
  • x(Tensor): The input tensor of adaptive max pool3d operator, which is a 5-D tensor. The data type can be float32, float64.

  • output(Tensor): The output tensor of adaptive max pool3d operator, which is a 5-D tensor. The data type is same as input x.

Returns

A callable object of AdaptiveMaxPool3D.

Examples

# adaptive max pool3d
# suppose input data in shape of [N, C, D, H, W], `output_size` is [l, m, n],
# output shape is [N, C, l, m, n], adaptive pool divide D, H and W dimensions
# of input data into l * m * n grids averagely and performs poolings in each
# grid to get output.
# adaptive max pool performs calculations as follow:
#
#     for i in range(l):
#         for j in range(m):
#             for k in range(n):
#                 dstart = floor(i * D / l)
#                 dend = ceil((i + 1) * D / l)
#                 hstart = floor(j * H / m)
#                 hend = ceil((j + 1) * H / m)
#                 wstart = floor(k * W / n)
#                 wend = ceil((k + 1) * W / n)
#                 output[:, :, i, j, k] =
#                     max(input[:, :, dstart:dend, hstart: hend, wstart: wend])
import paddle
import numpy as np

input_data = np.random.rand(2, 3, 8, 32, 32)
x = paddle.to_tensor(input_data)
pool = paddle.nn.AdaptiveMaxPool3D(output_size=4)
out = pool(x)
# out shape: [2, 3, 4, 4, 4]
pool = paddle.nn.AdaptiveMaxPool3D(output_size=3, return_mask=True)
out, indices = pool(x)
# out shape: [2, 3, 4, 4, 4], indices shape: [2, 3, 4, 4, 4]
forward ( x )

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters
  • *inputs (tuple) – unpacked tuple arguments

  • **kwargs (dict) – unpacked dict arguments

extra_repr ( )

Extra representation of this layer, you can have custom implementation of your own layer.