自定义参数初始化方法

def weight_init(m):
    if isinstance(m, nn.Linear):
        nn.init.xavier_normal_(m.weight)
        nn.init.constant_(m.bias, 0)
    # 也可以判断是否为conv2d，使用相应的初始化方式 
    elif isinstance(m, nn.Conv2d):
        nn.init.kaiming_normal_(m.weight, mode=\'fan_out\', nonlinearity=\'relu\')
     # 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)
# 2. 初始化网络结构        
model = Net(in_dim, n_hidden_1, n_hidden_2, out_dim)
# 3. 将weight_init应用在子模块上
model.apply(weight_init)

　　自定义参数初始化方法

原博客：https://blog.csdn.net/dss_dssssd/article/details/83990511

对某一层进行初始化

https://blog.csdn.net/VictoriaW/article/details/72872036

 

预训练部分不想加载

https://blog.csdn.net/qq_34914551/article/details/87871134