【报错分析】AttributeError: ‘NoneType‘ object has no attribute ‘fill‘

初始化问题;

    if init_weights:  # 是否使用初始化权重
            self._initialize_weights()


    def _initialize_weights(self):  # 初始化权重
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='leaky_relu')
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

 将上述代码改为：

        for m in self.modules():#参数初始化操作，遍历模型中的参数
            if isinstance(m, nn.Conv2d): #如果模型层是卷积层
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='leaky_relu') 
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                #nn.init.constant_(m.bias, 0)
            # 是否为批归一化层
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

AttributeError: ‘NoneType‘ object has no attribute ‘fill_‘_excelNo1的博客-CSDN博客

原因：

在Conv2d、Linear 和 BacthNorm2d 中设置了bias = True 才能赋值，否则需要注释bias 的赋值。