[開發技巧]·AdaptivePooling與Max/AvgPooling相互轉換

時間 2019-12-09

標籤開發技巧 adaptivepooling max avgpooling 相互轉換简体版

原文原文鏈接

[開發技巧]·AdaptivePooling與Max/AvgPooling相互轉換

我的網站--> http://www.yansongsong.cn/python

1.問題描述

自適應池化Adaptive Pooling是PyTorch的一種池化層，根據1D，2D，3D以及Max與Avg可分爲六種形式。c++

自適應池化Adaptive Pooling與標準的Max/AvgPooling區別在於，自適應池化Adaptive Pooling會根據輸入的參數來控制輸出output_size，而標準的Max/AvgPooling是經過kernel_size，stride與padding來計算output_size： git

output_size = ceil ( (input_size+2∗padding−kernel_size)/stride）+1github

Adaptive Pooling僅存在與PyTorch，若是須要將包含Adaptive Pooling的代碼移植到Keras或者TensorFlow就會遇到問題。bash

本文將提供一個公式，能夠簡便的將AdaptivePooling準換爲Max/AvgPooling，便於你們移植使用。app

2.原理講解

咱們已經知道了普通Max/AvgPooling計算公式爲：output_size = ceil ( (input_size+2∗padding−kernel_size)/stride）+1 框架

當咱們使用Adaptive Pooling時，這個問題就變成了由已知量input_size，output_size求解kernel_size與strideide

爲了簡化問題，咱們將padding設爲0（後面咱們能夠發現源碼裏也是這樣操做的c++源碼部分）學習

stride = floor ( (input_size / (output_size) )網站

kernel_size = input_size − (output_size−1) * stride

3.實戰演示

下面咱們經過一個實戰來操做一下，驗證公式的正確性

import torch as t
import math
import numpy as np

alist = t.randn(2,6,7)

inputsz = np.array(alist.shape[1:])
outputsz = np.array([2,3])

stridesz = np.floor(inputsz/outputsz).astype(np.int32)

kernelsz = inputsz-(outputsz-1)*stridesz

adp = t.nn.AdaptiveAvgPool2d(list(outputsz))
avg = t.nn.AvgPool2d(kernel_size=list(kernelsz),stride=list(stridesz))
adplist = adp(alist)
avglist = avg(alist)

print(alist)
print(adplist)
print(avglist)

輸出結果

tensor([[[ 0.9095,  0.8043,  0.4052,  0.3410,  1.8831,  0.8703, -0.0839],
         [ 0.3300, -1.2951, -1.8148, -1.1118, -1.1091,  1.5657,  0.7093],
         [-0.6788, -1.2790, -0.6456,  1.9085,  0.8627,  1.1711,  0.5614],
         [-0.0129, -0.6447, -0.6685, -1.2087,  0.8535, -1.4802,  0.5274],
         [ 0.7347,  0.0374, -1.7286, -0.7225, -0.4257, -0.0819, -0.9878],
         [-1.2553, -1.0774, -0.1936, -1.4741, -0.9028, -0.1584, -0.6612]],

        [[-0.3473,  1.0599, -1.5744, -0.2023, -0.5336,  0.5512, -0.3200],
         [-0.2518,  0.1714,  0.6862,  0.3334, -1.2693, -1.3348, -0.0878],
         [ 1.0515,  0.1385,  0.4050,  0.8554,  1.0170, -2.6985,  0.3586],
         [-0.1977,  0.8298,  1.6110, -0.9102,  0.7129,  0.2088,  0.9553],
         [-0.2218, -0.7234, -0.4407,  1.0369, -0.8884,  0.3684,  1.2134],
         [ 0.5812,  1.1974, -0.1584, -0.0903, -0.0628,  3.3684,  2.0330]]])


tensor([[[-0.3627,  0.0799,  0.7145],
         [-0.5343, -0.7190, -0.3686]],

        [[ 0.1488, -0.0314, -0.4797],
         [ 0.2753,  0.0900,  0.8788]]])

tensor([[[-0.3627,  0.0799,  0.7145],
         [-0.5343, -0.7190, -0.3686]],

        [[ 0.1488, -0.0314, -0.4797],
         [ 0.2753,  0.0900,  0.8788]]])

能夠發現adp = t.nn.AdaptiveAvgPool2d(list(outputsz))與avg = t.nn.AvgPool2d(kernel_size=list(kernelsz),stride=list(stridesz))結果一致

爲了防止這是偶然現象，修改參數，使用AdaptiveAvgPool1d進行試驗

import torch as t
import math
import numpy as np

alist = t.randn(2,3,9)

inputsz = np.array(alist.shape[2:])
outputsz = np.array([4])

stridesz = np.floor(inputsz/outputsz).astype(np.int32)

kernelsz = inputsz-(outputsz-1)*stridesz

adp = t.nn.AdaptiveAvgPool1d(list(outputsz))
avg = t.nn.AvgPool1d(kernel_size=list(kernelsz),stride=list(stridesz))
adplist = adp(alist)
avglist = avg(alist)

print(alist)
print(adplist)
print(avglist)

輸出結果

tensor([[[ 1.3405,  0.3509, -1.5119, -0.1730,  0.6971,  0.3399, -0.0874,
          -1.2417,  0.6564],
         [ 2.0482,  0.3528,  0.0703,  1.2012, -0.8829, -0.3156,  1.0603,
          -0.7722, -0.6086],
         [ 1.0470, -0.9374,  0.3594, -0.8068,  0.5126,  1.4135,  0.3538,
          -1.0973,  0.3046]],

        [[-0.1688,  0.7300, -0.3457,  0.5645, -1.2507, -1.9724,  0.4469,
          -0.3362,  0.7910],
         [ 0.5676, -0.0614, -0.0243,  0.1529,  0.8276,  0.2452, -0.1783,
           0.7460,  0.2577],
         [-0.1433, -0.7047, -0.4883,  1.2414, -1.4316,  0.9704, -1.7088,
          -0.0094, -0.3739]]])


tensor([[[ 0.0598, -0.3293,  0.3165, -0.2242],
         [ 0.8237,  0.1295, -0.0461, -0.1069],
         [ 0.1563,  0.0217,  0.7600, -0.1463]],

        [[ 0.0718, -0.3440, -0.9254,  0.3006],
         [ 0.1606,  0.3187,  0.2982,  0.2751],
         [-0.4454, -0.2262, -0.7233, -0.6973]]])

tensor([[[ 0.0598, -0.3293,  0.3165, -0.2242],
         [ 0.8237,  0.1295, -0.0461, -0.1069],
         [ 0.1563,  0.0217,  0.7600, -0.1463]],

        [[ 0.0718, -0.3440, -0.9254,  0.3006],
         [ 0.1606,  0.3187,  0.2982,  0.2751],
         [-0.4454, -0.2262, -0.7233, -0.6973]]])

能夠發現adp = t.nn.AdaptiveAvgPool1d(list(outputsz))與avg = t.nn.AvgPool1d(kernel_size=list(kernelsz),stride=list(stridesz))結果也是相同的。