【Pythorch】AlexNetで3次元データをクラス分類したいが、MaxPool3dの使い方がわからない

前提・実現したいこと

Python初心者です。

AlexNetで3次元データをクラス分類したいのですが、MaxPool3dの使い方がわからず
RuntimeErrorになってしまいます。nn.Conv3d部分も正しいかわかりません。

間違っている箇所あればご指摘いただけますと幸いです。

発生している問題・エラーメッセージ

$ python AlexNet.py 
Traceback (most recent call last):                                                                                                                 
  File "AlexNet.py", line 134, in <module>
    outputs = net(images)
  File "/home/selen/.pyenv/versions/3.7.3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in __call__
    result = self.forward(*input, **kwargs)
  File "AlexNet.py", line 107, in forward
    x = self.features(x)
  File "/home/selen/.pyenv/versions/3.7.3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/selen/.pyenv/versions/3.7.3/lib/python3.7/site-packages/torch/nn/modules/container.py", line 92, in forward
    input = module(input)
  File "/home/selen/.pyenv/versions/3.7.3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/selen/.pyenv/versions/3.7.3/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 476, in forward
    self.padding, self.dilation, self.groups)
RuntimeError: Expected 5-dimensional input for 5-dimensional weight 64 3 3 3, but got 4-dimensional input of size [64, 80, 96, 80] instead

該当のソースコード

Python
1class AlexNet(nn.Module):
2
3    def __init__(self, num_classes):
4        super(AlexNet, self).__init__()
5        self.features = nn.Sequential(
6            nn.Conv3d(3, 64, kernel_size=3, padding=1),
7            nn.ReLU(inplace=True),
8            nn.MaxPool3d((80, 96, 80), stride=(2, 2, 2)),
9            
10            nn.Conv3d(64, 192, kernel_size=5, padding=2),
11            nn.ReLU(inplace=True),
12            nn.MaxPool3d((80, 96, 80), stride=(2, 2, 2)),
13            
14            nn.Conv3d(192, 384, kernel_size=3, padding=1),
15            nn.ReLU(inplace=True),
16            
17            nn.Conv3d(384, 256, kernel_size=3, padding=1),
18            nn.ReLU(inplace=True),
19            
20            nn.Conv3d(256, 256, kernel_size=3, padding=1),
21            nn.ReLU(inplace=True),
22            nn.MaxPool3d((80, 96, 80), stride=(2, 2, 2)),
23        )
24
25        self.classifier = nn.Sequential(
26            nn.Dropout(),
27            nn.Linear(256 * 4 * 4, 4096),
28            nn.ReLU(inplace=True),
29
30            nn.Dropout(),
31            nn.Linear(4096, 4096),
32            nn.ReLU(inplace=True),
33
34            nn.Linear(4096, num_classes),
35        )
36
37    def forward(self, x):
38        x = self.features(x)
39        x = x.view(x.size(0), 256 * 4 * 4)
40        x = self.classifier(x)
41        return x
42