1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31

# 查看随机初始化的conv参数
conv.weight.data
# 查看linear的参数
linear.weight.data
tensor([[[[ 0.1174,  0.1071,  0.2977],
          [-0.2634, -0.0583, -0.2465],
          [ 0.1726, -0.0452, -0.2354]]],
        [[[ 0.1382,  0.1853, -0.1515],
          [ 0.0561,  0.2798, -0.2488],
          [-0.1288,  0.0031,  0.2826]]],
        [[[ 0.2655,  0.2566, -0.1276],
          [ 0.1905, -0.1308,  0.2933],
          [ 0.0557, -0.1880,  0.0669]]]])
tensor([[-0.0089,  0.1186,  0.1213, -0.2569,  0.1381,  0.3125,  0.1118, -0.0063, -0.2330,  0.1956]])
# 对conv进行kaiming初始化
torch.nn.init.kaiming_normal_(conv.weight.data)
conv.weight.data
# 对linear进行常数初始化
torch.nn.init.constant_(linear.weight.data,0.3)
linear.weight.data
tensor([[[[ 0.3249, -0.0500,  0.6703],
          [-0.3561,  0.0946,  0.4380],
          [-0.9426,  0.9116,  0.4374]]],
        [[[ 0.6727,  0.9885,  0.1635],
          [ 0.7218, -1.2841, -0.2970],
          [-0.9128, -0.1134, -0.3846]]],
        [[[ 0.2018,  0.4668, -0.0937],
          [-0.2701, -0.3073,  0.6686],
          [-0.3269, -0.0094,  0.3246]]]])
tensor([[0.3000, 0.3000, 0.3000, 0.3000, 0.3000, 0.3000, 0.3000, 0.3000, 0.3000,0.3000]])

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42

# 模型的定义
class MLP(nn.Module):
  # 声明带有模型参数的层，这里声明了两个全连接层
  def __init__(self, **kwargs):
    # 调用MLP父类Block的构造函数来进行必要的初始化。这样在构造实例时还可以指定其他函数
    super(MLP, self).__init__(**kwargs)
    self.hidden = nn.Conv2d(1,1,3)
    self.act = nn.ReLU()
    self.output = nn.Linear(10,1)
       # 定义模型的前向计算，即如何根据输入x计算返回所需要的模型输出
  def forward(self, x):
    o = self.act(self.hidden(x))
    return self.output(o)
mlp = MLP()
print(list(mlp.parameters()))
print("-------初始化-------")
initialize_weights(mlp)
print(list(mlp.parameters()))
[Parameter containing:
tensor([[[[ 0.2103, -0.1679,  0.1757],
          [-0.0647, -0.0136, -0.0410],
          [ 0.1371, -0.1738, -0.0850]]]], requires_grad=True), Parameter containing:
tensor([0.2507], requires_grad=True), Parameter containing:
tensor([[ 0.2790, -0.1247,  0.2762,  0.1149, -0.2121, -0.3022, -0.1859,  0.2983,
         -0.0757, -0.2868]], requires_grad=True), Parameter containing:
tensor([-0.0905], requires_grad=True)]
"-------初始化-------"
[Parameter containing:
 tensor([[[[-0.3196, -0.0204, -0.5784],
           [ 0.2660,  0.2242, -0.4198],
           [-0.0952,  0.6033, -0.8108]]]], requires_grad=True),
 Parameter containing:
 tensor([0.3000], requires_grad=True),
 Parameter containing:
 tensor([[ 0.7542,  0.5796,  2.2963, -0.1814, -0.9627,  1.9044,  0.4763,  1.2077,
           0.8583,  1.9494]], requires_grad=True),
 Parameter containing:
 tensor([0.], requires_grad=True)]