AttributeError: 'ResidualBlock' object has no attribute 'conv'

这个错误提示表明在`ResidualBlock`对象中没有名为`conv`的属性。这可能是因为您在定义`ResidualBlock`类时没有正确地初始化该属性。

以下是一个修正的例子：

 def __init__(self, inchannel, outchannel):
 super(ResidualBlock, self).__init__()
 self.conv1 = nn.Conv2d(inchannel, outchannel, kernel_size=3, stride=1, padding=1)
 self.relu = nn.ReLU()
 self.conv2 = nn.Conv2d(outchannel, outchannel, kernel_size=3, stride=1, padding=1)
 self.bn = nn.BatchNorm2d(outchannel)

 def forward(self, x):
 residual = x out = self.conv1(x)
 out = self.relu(out)
 out = self.conv2(out)
 out = self.bn(out)
 out += residual out = self.relu(out)
 return out# 创建残差块实例in_channels =64out_channels =128residual_block = ResidualBlock(in_channels, out_channels)

# 使用残差块进行前向传播x = torch.randn(1, in_channels,32,32)
output = residual_block(x)

请注意，我在`ResidualBlock`类中添加了`conv1`和`conv2`属性，并在`forward`函数中使用了这些属性。请根据您的实际需求调整代码中的参数和网络结构。

如果您还遇到其他问题，请随时提问！