pytorch初始化模型参数

定义初始化模型方法

运用apply(）

from torch.nn import init
# define the initial function to init the layer's parameters for the networks
def weight_init(m):
	if isinstance(m, nn.Conv2d):
		nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
	elif isinstance(m, nn.Linear):
		nn.init.xavier_normal_(m.weight)
		nn.init.constant_(m.bias, 0)
	elif isinstance(m, nn.BatchNorm2d):
        nn.init.constant_(m.weight, 1)
        nn.init.constant_(m.bias, 0)
      
# 还有另一种初始化的方式可供参考
def weigth_init(m):
    if isinstance(m, nn.Conv2d):
        init.xavier_uniform_(m.weight.data)
        init.constant_(m.bias.data,0.1)
    elif isinstance(m, nn.BatchNorm2d):
        m.weight.data.fill_(1)
        m.bias.data.zero_()
    elif isinstance(m, nn.Linear):
        m.weight.data.normal_(0,0.01)
        m.bias.data.zero_()

定义在模型中，利用self.modules()来进行循环

class Net(nn.Module):
    def __init__(self, in_dim, n_hidden_1, n_hidden_2, out_dim):
        super().__init__()

        self.layer = nn.Sequential(
            nn.Linear(in_dim, n_hidden_1), 
            nn.ReLU(True),
            nn.Linear(n_hidden_1, n_hidden_2),
            nn.ReLU(True),
            nn.Linear(n_hidden_2, out_dim)
            
             )    
       for m in self.modules():
             if isinstance(m, nn.Conv2d):
                 nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
             elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
                 nn.init.constant_(m.weight, 1)
                 nn.init.constant_(m.bias, 0)
    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        return x

另外，在pytorch中，有自己默认初始化参数方式，在定义好网络结构后，不进行参数初始化可以使可以的
Conv2d 继承自 _ConvNd，在_ConvNd中，可以看到默认参数就是进行初始化的，torch.nn.BatchNorm2d 和 torch.nn.Linear 也如此