预训练的vgg网络提取中间层的两种使用方法，可拓展至其它预训练的网络

方法一

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
from collections import namedtuple
import torch
import torch.nn as nn
from torchvision import models

class Vgg16(torch.nn.Module):
    def __init__(self, requires_grad=False):
        super(Vgg16, self).__init__()
        vgg_pretrained_features = models.vgg16(pretrained=True).features  # 只保留提取特征的层(features)，classifier不需要
        # 首次使用vgg16需要设置pretrained=True下载权重参数
        self.slice1 = torch.nn.Sequential()
        self.slice2 = torch.nn.Sequential()
        self.slice3 = torch.nn.Sequential()
        self.slice4 = torch.nn.Sequential()
        for x in range(4):
            self.slice1.add_module(str(x), vgg_pretrained_features[x])
        for x in range(4, 9):
            self.slice2.add_module(str(x), vgg_pretrained_features[x])
        for x in range(9, 16):
            self.slice3.add_module(str(x), vgg_pretrained_features[x])
        for x in range(16, 23):
            self.slice4.add_module(str(x), vgg_pretrained_features[x])
        if not requires_grad:
            for param in self.parameters():
                param.requires_grad = False

    def forward(self, X):
        h = self.slice1(X)
        h_relu1_2 = h
        h = self.slice2(h)
        h_relu2_2 = h
        h = self.slice3(h)
        h_relu3_3 = h
        h = self.slice4(h)
        h_relu4_3 = h
        vgg_outputs = namedtuple("VggOutputs", ['relu1_2', 'relu2_2', 'relu3_3', 'relu4_3'])
        out = vgg_outputs(h_relu1_2, h_relu2_2, h_relu3_3, h_relu4_3)
        return out

方法二

1
2
3
4
5
6
7
8
9
10
11
12
13
14
class VGGNet(nn.Module):
    def __init__(self):
        super(VGGNet, self).__init__()
        self.select = ['5', '10', '19', '28'] 
        # 选择输出某些层的输出，按需更改
        self.vgg = models.vgg19(pretrained=True).features
        
    def forward(self, x):
        features = []
        for name, layer in self.vgg._modules.items():
            x = layer(x)
            if name in self.select:
                features.append(x)
        return features

VGG6由两部分构成，features和classifier。
使用models.vgg16(pretrained=True).features便可提出features
features结构如下

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
(features): Sequential(
    (0): Conv2d (3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU(inplace)
    (2): Conv2d (64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU(inplace)
    (4): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), dilation=(1, 1))
    (5): Conv2d (64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (6): ReLU(inplace)
    (7): Conv2d (128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (8): ReLU(inplace)
    (9): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), dilation=(1, 1))
    (10): Conv2d (128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace)
    (12): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (13): ReLU(inplace)
    (14): Conv2d (256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (15): ReLU(inplace)
    (16): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), dilation=(1, 1))
    (17): Conv2d (256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (18): ReLU(inplace)
    (19): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (20): ReLU(inplace)
    (21): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (22): ReLU(inplace)
    (23): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), dilation=(1, 1))
    (24): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (25): ReLU(inplace)
    (26): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (27): ReLU(inplace)
    (28): Conv2d (512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (29): ReLU(inplace)
    (30): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), dilation=(1, 1))
  )

方法一按照需求将其重组在多个Sequential内，以便网络返回中间结果
方法二则提取出select列表内对应层的特征，将其放入一个列表，最后将其返回

classifier在这里没有使用
在迁移学习中常常会更改最后Linear层的输出维度，后面会介绍。
使用models.vgg16(pretrained=True).classifier可拿出classifier

1
2
3
4
5
6
7
8
9
(classifier): Sequential(
  (0): Linear(in_features=25088, out_features=4096)
  (1): ReLU(inplace)
  (2): Dropout(p=0.5)
  (3): Linear(in_features=4096, out_features=4096)
  (4): ReLU(inplace)
  (5): Dropout(p=0.5)
  (6): Linear(in_features=4096, out_features=1000)
)