文章目录
前言
在使用pytorch构建神经网络时，定义的网络模型必须要继承自torch.nn.Module这一父类。在Module类中，有一个函数可以返回网络中所有模块的迭代器。这就是torch.nn.Module.modules()
提示：以下是本篇文章正文内容，下面案例可供参考
一、torch.nn.Module.modules()
源码中的解释如下：
bash
def modules(self) -> Iterator['Module']:
r"""Returns an iterator over all modules in the network.
Yields:
Module: a module in the network
Note:
Duplicate modules are returned only once. In the following
example, ``l`` will be returned only once.
Example::
>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.modules()):
print(idx, '->', m)
0 -> Sequential(
(0): Linear(in_features=2, out_features=2, bias=True)
(1): Linear(in_features=2, out_features=2, bias=True)
)
1 -> Linear(in_features=2, out_features=2, bias=True)
"""
for _, module in self.named_modules():
yield module不只是返回网络中的某一层，而是所有模块和每一层，例如，在下面的代码中，我首先定义了VGG16的网络结构，然后打印出VGG16的modules()
结果如下：
bash
E:\study\python\anaconda\envs\graduate_project\python.exe E:/study/project/compute_vision/VGG/model.py
0 -> VGG16(
(features): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU()
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU()
(4): MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU()
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU()
(9): MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU()
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU()
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU()
(16): MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
(17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(18): ReLU()
(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU()
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU()
(23): MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
(24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(25): ReLU()
(26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(27): ReLU()
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU()
(30): MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
)
(classifier): Sequential(
(0): Dropout(p=0.5, inplace=False)
(1): Linear(in_features=25088, out_features=4096, bias=True)
(2): Dropout(p=0.5, inplace=False)
(3): Linear(in_features=4096, out_features=4096, bias=True)
(4): Linear(in_features=4096, out_features=1000, bias=True)
)
)
1 -> Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU()
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU()
(4): MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU()
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU()
(9): MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU()
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU()
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU()
(16): MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
(17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(18): ReLU()
(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU()
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU()
(23): MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
(24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(25): ReLU()
(26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(27): ReLU()
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU()
(30): MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
)
2 -> Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
3 -> ReLU()
4 -> Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
5 -> ReLU()
6 -> MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
7 -> Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
8 -> ReLU()
9 -> Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
10 -> ReLU()
11 -> MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
12 -> Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
13 -> ReLU()
14 -> Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
15 -> ReLU()
16 -> Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
17 -> ReLU()
18 -> MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
19 -> Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
20 -> ReLU()
21 -> Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
22 -> ReLU()
23 -> Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
24 -> ReLU()
25 -> MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
26 -> Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
27 -> ReLU()
28 -> Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
29 -> ReLU()
30 -> Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
31 -> ReLU()
32 -> MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
33 -> Sequential(
(0): Dropout(p=0.5, inplace=False)
(1): Linear(in_features=25088, out_features=4096, bias=True)
(2): Dropout(p=0.5, inplace=False)
(3): Linear(in_features=4096, out_features=4096, bias=True)
(4): Linear(in_features=4096, out_features=1000, bias=True)
)
34 -> Dropout(p=0.5, inplace=False)
35 -> Linear(in_features=25088, out_features=4096, bias=True)
36 -> Dropout(p=0.5, inplace=False)
37 -> Linear(in_features=4096, out_features=4096, bias=True)
38 -> Linear(in_features=4096, out_features=1000, bias=True)
Process finished with exit code 0序号0：整个VGG16模块，包括特征提取模块和分类模块
序号1：特征提取模块
序号2-32：特征提取模块的每一层
序号33：分类模块
序号34-38：分类模块的每一层