Pytorch学习（三）self.modules()和self.children()的用法

通过代码来学习self.modules()和self.children()的用法.

1. self.children()和self.modules()测试代码

import torch
import torch.nn as nn
 
input_nc = 3
hide1_nc = 6
hide2_nc = 6
output_nc = 3
 
class Net(nn.Module):
    def __init__(self, input_nc, hide1_nc, hide2_nc, output_nc):
        super().__init__()

        self.layer1 = nn.Sequential(
            nn.Linear(input_nc, hide1_nc),
            nn.ReLU(inplace=True),
            nn.Linear(hide1_nc, hide2_nc),
            nn.ReLU(inplace=True)
        )
 
        self.layer2 = nn.Sequential(
            nn.Linear(hide1_nc, hide2_nc),
            nn.ReLU(inplace=True))
 
        self.layer3 = nn.Linear(hide2_nc, output_nc)
 
        print('self.children()测试')
        for i, j in enumerate(self.children()):
            print("第{}次循环\n{}".format(i, j))
            print('--' * 20)
 
        print('self.modules()测试')
        for i, j in enumerate(self.modules()):
            print("第{}次循环\n{}".format(i, j))
            print('--' * 20)
 
    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
 
        return x
 
model = Net(input_nc, hide1_nc, hide2_nc, output_nc)

2. 结果展示

self.children()测试
第0次循环
Sequential(
  (0): Linear(in_features=3, out_features=6, bias=True)
  (1): ReLU(inplace=True)
  (2): Linear(in_features=6, out_features=6, bias=True)
  (3): ReLU(inplace=True)
)
----------------------------------------
第1次循环
Sequential(
  (0): Linear(in_features=6, out_features=6, bias=True)
  (1): ReLU(inplace=True)
)
----------------------------------------
第2次循环
Linear(in_features=6, out_features=3, bias=True)
----------------------------------------
self.modules()测试
第0次循环
Net(
  (layer1): Sequential(
    (0): Linear(in_features=3, out_features=6, bias=True)
    (1): ReLU(inplace=True)
    (2): Linear(in_features=6, out_features=6, bias=True)
    (3): ReLU(inplace=True)
  )
  (layer2): Sequential(
    (0): Linear(in_features=6, out_features=6, bias=True)
    (1): ReLU(inplace=True)
  )
  (layer3): Linear(in_features=6, out_features=3, bias=True)
)
----------------------------------------
第1次循环
Sequential(
  (0): Linear(in_features=3, out_features=6, bias=True)
  (1): ReLU(inplace=True)
  (2): Linear(in_features=6, out_features=6, bias=True)
  (3): ReLU(inplace=True)
)
----------------------------------------
第2次循环
Linear(in_features=3, out_features=6, bias=True)
----------------------------------------
第3次循环
ReLU(inplace=True)
----------------------------------------
第4次循环
Linear(in_features=6, out_features=6, bias=True)
----------------------------------------
第5次循环
ReLU(inplace=True)
----------------------------------------
第6次循环
Sequential(
  (0): Linear(in_features=6, out_features=6, bias=True)
  (1): ReLU(inplace=True)
)
----------------------------------------
第7次循环
Linear(in_features=6, out_features=6, bias=True)
----------------------------------------
第8次循环
ReLU(inplace=True)
----------------------------------------
第9次循环
Linear(in_features=6, out_features=3, bias=True)
----------------------------------------

3. 结果分析

整体网络结构如下图所示：

由第二部分的测试结果可以看出，self.children()存储的是网络结构的子层模块，如下：

Sequential(
  (0): Linear(in_features=3, out_features=6, bias=True)
  (1): ReLU(inplace=True)
  (2): Linear(in_features=6, out_features=6, bias=True)
  (3): ReLU(inplace=True)
)
----------------------------------------
Sequential(
  (0): Linear(in_features=6, out_features=6, bias=True)
  (1): ReLU(inplace=True)
)
----------------------------------------
Linear(in_features=6, out_features=3, bias=True)
----------------------------------------

self.module()采用深度优先搜索的方式，存储了net的所有模块，包括网络模块本身及其所有后代模块，如下：

Net(
  (layer1): Sequential(
    (0): Linear(in_features=3, out_features=6, bias=True)
    (1): ReLU(inplace=True)
    (2): Linear(in_features=6, out_features=6, bias=True)
    (3): ReLU(inplace=True)
  )
  (layer2): Sequential(
    (0): Linear(in_features=6, out_features=6, bias=True)
    (1): ReLU(inplace=True)
  )
  (layer3): Linear(in_features=6, out_features=3, bias=True)
)
----------------------------------------
Sequential(
  (0): Linear(in_features=3, out_features=6, bias=True)
  (1): ReLU(inplace=True)
  (2): Linear(in_features=6, out_features=6, bias=True)
  (3): ReLU(inplace=True)
)
----------------------------------------
Linear(in_features=3, out_features=6, bias=True)
----------------------------------------
ReLU(inplace=True)
----------------------------------------
Linear(in_features=6, out_features=6, bias=True)
----------------------------------------
ReLU(inplace=True)
----------------------------------------
Sequential(
  (0): Linear(in_features=6, out_features=6, bias=True)
  (1): ReLU(inplace=True)
)
----------------------------------------
Linear(in_features=6, out_features=6, bias=True)
----------------------------------------
ReLU(inplace=True)
----------------------------------------
Linear(in_features=6, out_features=3, bias=True)
----------------------------------------