欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  IT编程

pytorch forward两个参数实例

程序员文章站 2022-06-12 18:33:41
以channel attention block为例子 class cab(nn.module): def __init__(self, in_channels,...

以channel attention block为例子

class cab(nn.module):
 
  def __init__(self, in_channels, out_channels):
    super(cab, self).__init__()
    self.global_pooling = nn.adaptiveavgpool2d(output_size=1)
    self.conv1 = nn.conv2d(in_channels, out_channels, kernel_size=1, stride=1, padding=0)
    self.relu = nn.relu()
    self.conv2 = nn.conv2d(out_channels, out_channels, kernel_size=1, stride=1, padding=0)
    self.sigmod = nn.sigmoid()
 
  def forward(self, x):
    x1, x2 = x # high, low
    x = torch.cat([x1,x2],dim=1)
    x = self.global_pooling(x)
    x = self.conv1(x)
    x = self.relu(x)
    x = self.conv2(x)
    x = self.sigmod(x)
    x2 = x * x2
    res = x2 + x1
    return res

以上这篇pytorch forward两个参数实例就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。