python-用numpy实现最大/平均池化(跨步)

我想知道如何使用numpy实现简单的最大/平均池.我正在阅读Max and mean pooling with numpy,但不幸的是,它假定步幅与内核大小相同.有numnumic的方法来做到这一点吗？如果这适用于任何维度,也很不错,但是当然不是必需的.

解决方法:

这是一个使用stride_tricks的纯numpy实现：

import numpy as np
from numpy.lib.stride_tricks import as_strided

def pool2d(A, kernel_size, stride, padding, pool_mode='max'):
    '''
    2D Pooling

    Parameters:
        A: input 2D array
        kernel_size: int, the size of the window
        stride: int, the stride of the window
        padding: int, implicit zero paddings on both sides of the input
        pool_mode: string, 'max' or 'avg'
    '''
    # Padding
    A = np.pad(A, padding, mode='constant')

    # Window view of A
    output_shape = ((A.shape[0] - kernel_size)//stride + 1,
                    (A.shape[1] - kernel_size)//stride + 1)
    kernel_size = (kernel_size, kernel_size)
    A_w = as_strided(A, shape = output_shape + kernel_size, 
                        strides = (stride*A.strides[0],
                                   stride*A.strides[1]) + A.strides)
    A_w = A_w.reshape(-1, *kernel_size)

    # Return the result of pooling
    if pool_mode == 'max':
        return A_w.max(axis=(1,2)).reshape(output_shape)
    elif pool_mode == 'avg':
        return A_w.mean(axis=(1,2)).reshape(output_shape)

例：

A = np.array([[1, 1, 2, 4],
              [5, 6, 7, 8],
              [3, 2, 1, 0],
              [1, 2, 3, 4]])

pool2d(A, kernel_size=2, stride=2, padding=0, pool_mode='max')

array([[6, 8],
       [3, 4]])

https://cs231n.github.io/convolutional-networks/

标签：python-3-x,conv-neural-network,python,numpy
来源： https://codeday.me/bug/20191024/1923044.html