【Pytorch + AlexNet + torchsummary】torchsummary 查看网 及 各层输出的 feature map 尺寸

import torch
import torch.nn as nn
from torchsummary import summary


class AlexNet(nn.Module):
    def __init__(self, num_classes=1000):
        super().__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 96, kernel_size=11, stride=4, padding=2),  # [None, 3, 224, 224] --> [None, 96, 55, 55]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),  # [None, 96, 55, 55] --> [None, 96, 27, 27]
            nn.Conv2d(96, 256, kernel_size=5, padding=2),  # [None, 96, 27, 27] --> [None, 256, 27, 27]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),  # [None, 256, 27, 27] --> [None, 256, 13, 13]
            nn.Conv2d(256, 384, kernel_size=3, padding=1),  # [None, 256, 27, 27] --> [None, 384, 13, 13]
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 384, kernel_size=3, padding=1),  # [None, 384, 13, 13] --> [None, 384, 13, 13]
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 256, kernel_size=3, padding=1),  # [None, 384, 13, 13] --> [None, 256, 13, 13]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2)  # [None, 256, 13, 13] --> [None, 256, 6, 6]
        )

        self.classifier = nn.Sequential(
            nn.Dropout(p=0.2),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(p=0.2),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, num_classes)
        )

    def forward(self, inputs):
        x = self.features(inputs)
        x = torch.flatten(x, start_dim=1)
        outputs = self.classifier(x)
        return outputs


device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = AlexNet(1000).to(device)
summary(model, (3, 224, 224))

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
43
44
45

输出：

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1           [-1, 96, 55, 55]          34,944
              ReLU-2           [-1, 96, 55, 55]               0
         MaxPool2d-3           [-1, 96, 27, 27]               0
            Conv2d-4          [-1, 256, 27, 27]         614,656
              ReLU-5          [-1, 256, 27, 27]               0
         MaxPool2d-6          [-1, 256, 13, 13]               0
            Conv2d-7          [-1, 384, 13, 13]         885,120
              ReLU-8          [-1, 384, 13, 13]               0
            Conv2d-9          [-1, 384, 13, 13]       1,327,488
             ReLU-10          [-1, 384, 13, 13]               0
           Conv2d-11          [-1, 256, 13, 13]         884,992
             ReLU-12          [-1, 256, 13, 13]               0
        MaxPool2d-13            [-1, 256, 6, 6]               0
          Dropout-14                 [-1, 9216]               0
           Linear-15                 [-1, 4096]      37,752,832
             ReLU-16                 [-1, 4096]               0
          Dropout-17                 [-1, 4096]               0
           Linear-18                 [-1, 4096]      16,781,312
             ReLU-19                 [-1, 4096]               0
           Linear-20                 [-1, 1000]       4,097,000
================================================================
Total params: 62,378,344
Trainable params: 62,378,344
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 11.09
Params size (MB): 237.95
Estimated Total Size (MB): 249.62
----------------------------------------------------------------
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