簡介

自適應池化Adaptive Pooling是PyTorch含有的一種池化層，在PyTorch的中有六種形式：

自適應最大池化Adaptive Max Pooling：

torch.nn.AdaptiveMaxPool1d(output_size)
torch.nn.AdaptiveMaxPool2d(output_size)
torch.nn.AdaptiveMaxPool3d(output_size)

自適應平均池化Adaptive Average Pooling：

torch.nn.AdaptiveAvgPool1d(output_size)
torch.nn.AdaptiveAvgPool2d(output_size)

具體可見官方文件。

官方給出的例子：
>>> # target output size of 5x7
>>> m = nn.AdaptiveMaxPool2d((5,7))
>>> input = torch.randn(1,64,8,9)
>>> output = m(input)
>>> output.size()
torch.Size([1,5,7])

>>> # target output size of 7x7 (square)
>>> m = nn.AdaptiveMaxPool2d(7)
>>> input = torch.randn(1,10,7,7])

>>> # target output size of 10x7
>>> m = nn.AdaptiveMaxPool2d((None,7])

Adaptive Pooling特殊性在於，輸出張量的大小都是給定的output_size output\_sizeoutput_size。例如輸入張量大小為(1,9)，設定輸出大小為(5,7)，通過Adaptive Pooling層，可以得到大小為(1,7)的張量。

原理

>>> inputsize = 9
>>> outputsize = 4

>>> input = torch.randn(1,1,inputsize)
>>> input
tensor([[[ 1.5695,-0.4357,1.5179,0.9639,-0.4226,0.5312,-0.5689,0.4945,0.1421]]])

>>> m1 = nn.AdaptiveMaxPool1d(outputsize)
>>> m2 = nn.MaxPool1d(kernel_size=math.ceil(inputsize / outputsize),stride=math.floor(inputsize / outputsize),padding=0)
>>> output1 = m1(input)
>>> output2 = m2(input)

>>> output1
tensor([[[1.5695,0.4945]]]) torch.Size([1,4])
>>> output2
tensor([[[1.5695,4])

通過實驗發現：

下面是Adaptive Average Pooling的c++原始碼部分。

 template <typename scalar_t>
 static void adaptive_avg_pool2d_out_frame(
      scalar_t *input_p,scalar_t *output_p,int64_t sizeD,int64_t isizeH,int64_t isizeW,int64_t osizeH,int64_t osizeW,int64_t istrideD,int64_t istrideH,int64_t istrideW)
 {
  int64_t d;
 #pragma omp parallel for private(d)
  for (d = 0; d < sizeD; d++)
  {
   /* loop over output */
   int64_t oh,ow;
   for(oh = 0; oh < osizeH; oh++)
   {
    int istartH = start_index(oh,osizeH,isizeH);
    int iendH  = end_index(oh,isizeH);
    int kH = iendH - istartH;

    for(ow = 0; ow < osizeW; ow++)
    {
     int istartW = start_index(ow,osizeW,isizeW);
     int iendW  = end_index(ow,isizeW);
     int kW = iendW - istartW;

     /* local pointers */
     scalar_t *ip = input_p  + d*istrideD + istartH*istrideH + istartW*istrideW;
     scalar_t *op = output_p + d*osizeH*osizeW + oh*osizeW + ow;

     /* compute local average: */
     scalar_t sum = 0;
     int ih,iw;
     for(ih = 0; ih < kH; ih++)
     {
      for(iw = 0; iw < kW; iw++)
      {
       scalar_t val = *(ip + ih*istrideH + iw*istrideW);
       sum += val;
      }
     }

     /* set output to local average */
     *op = sum / kW / kH;
    }
   }
  }
}

以上這篇PyTorch的自適應池化Adaptive Pooling例項就是小編分享給大家的全部內容了，希望能給大家一個參考，也希望大家多多支援我們。