MaxPool3D

Description

Info

Parent class: Pool3D

Derived classes: -

This module implements the operation of three-dimensional max pooling. For a detailed theoretical description, please see Pool3D.

For an input tensor of shape $(N, C, D_{in}, H_{in}, W_{in})$ and the output one of shape $(N, C, D_{out}, H_{out}, W_{out})$ the operation is performed as follows (we consider the i-th element of the batch and the j-th map of the output tensor):

$$out(N_i, C_j, d, h, w) = \max\limits_{t=0..k_d-1}\max\limits_{m=0..k_h-1}\max\limits_{n=0..k_w-1}(input(N_i, C_j, stride_d \times d + t, stride_h \times h + m, stride_w \times w + n))$$

where

$N$ - size of the batch;
$C$ - number of maps in the tensor;
$H$ - tensor map height;
$W$ - tensor map width;
$stride_d, stride_h, stride_w$ - pooling stride along the depth, height and width of the maps, respectively;
$k_d, k_h, k_w$ - size of the pooling kernel in depth, height and width, respectively.

Initializing

def __init__(self, size=2, stride=2, pad=0, name=None):

Parameters

Parameter	Allowed types	Description	Default
size	Union[int, tuple]	Kernel size	2
stride	Union[int, tuple]	Pooling stride	2
pad	Union[int, tuple]	Input maps padding	0
name	str	Layer name	None

Explanations

size - possible to specify either a single size of the pooling kernel, in which case it will be cubic, or a tuple (size_d, size_h, size_w), where size_d is the depth of the pooling kernel, size_h is the height of the pooling kernel, and size_w is its width;

---

stride - possible to specify either a single value of the pooling stride along all the axes of the map, or a tuple (stride_d, stride_h, stride_w), where stride_d is the value of the pooling stride along the depth of the map, stride_h is the value of the pooling stride along the map height, and stride_w is along the width;

---

pad - possible to specify either a single padding value for all sides of the maps, or a tuple (pad_d, pad_h, pad_w), where pad_d is the padding value on each side along the depth of the map, pad_h is along the height of the map, and pad_w is along the width.

---

Important

If you set any of the size, stride or pad parameters different for the map axes, then the values of these parameters must be explicitly specified in a three-element tuple, otherwise an error will occur.

Examples

---

Necessary imports.

>>> import numpy as np
>>> from PuzzleLib.Backend import gpuarray
>>> from PuzzleLib.Modules import MaxPool3D

Info

gpuarray is required to properly place the tensor in the GPU

For this module, the examples are given in a simplified version. For a more visual presentation, you can take a look at the examples in MaxPool2D.

>>> batchsize, maps, d, h, w = 1, 1, 6, 6, 6
>>> data = gpuarray.to_gpu(np.random.randn(batchsize, maps, d, h, w).astype(np.float32))

Let us initialize a module with standard parameters (size=2, stride=2, pad=0):

>>> avgpool = MaxPool3D()
>>> avgpool(data)

Let us leave all parameters the same size:

>>> pool = MaxPool3D(size=4)
>>> pool(data)

The size parameter can be set different for each axis of the map:

>>> pool = MaxPool3D(size=(2, 4, 2))
>>> pool(data)

The stride and pad parameters can also be set different for each axis of the map:

>>> pool = MaxPool3D(size=4, stride=(1, 4, 4), pad=(0, 1, 1))
>>> pool(data)

As mentioned earlier, if the parameter has different values for different axes, then all these values must be passed explicitly. The following example will throw an error:

>>> pool = MaxPool3D(stride=(1, 3))
>>> pool(data)