Pytorch上下采样函数--interpolate

torch.nn的上下采样，只能是8的倍数，不能任意分辨率。

       self.upsample= nn.Upsample(scale_factor=2,mode='nearest', align_corners=None)#, mode='bilinear', align_corners=False)
       self.p3_downsample = nn.MaxPool2d(kernel_size=2)
  
 

enet下采样 

      class DownsamplingBottleneck(nn.Module):
      def __init__(self,
       in_channels,
       out_channels,
       internal_ratio=4,
       return_indices=False,
       dropout_prob=0,
       bias=False,
       relu=True):
       super().__init__()
      # Store parameters that are needed later
       self.return_indices = return_indices
      # Check in the internal_scale parameter is within the expected range
      # [1, channels]
      if internal_ratio <= 1 or internal_ratio > in_channels:
       rais
  
 

文章来源: blog.csdn.net，作者：网奇，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/jacke121/article/details/103976455