AlexNetで画像分類したいがRuntimeErrorになってしまう

前提・実現したいこと

Python初心者です。
AlexNetで3次元データを画像分類したいのですが、RuntimeErrorになってしまいます。
間違っている箇所あればご指摘していただけると幸いです。

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 "test.py", line 127, 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 "test.py", line 100, 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

import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D

import torch
import torchvision
import torch.nn as nn
import torch.nn.init as init
import torch.optim as optim
import torch.nn.functional as F
import torchvision.transforms as transforms
import numpy as np
from matplotlib import pyplot as plt
from skimage import io, transform

from torch.utils.data import Dataset
from dataset import CLASS_MAP
import dataset

CLASS_MAP = {"CN": 0, "AD": 1, "LMCI": 2, "SMC": 3, "EMCI": 4}

class BrainData(Dataset):
    def __init__(self, data, transform=None, class_map=CLASS_MAP):
        self.data = data
        self.class_map = class_map
        self.transform = transform

    def __len__(self):
        return len(self.data)

    def __getitem__(self, idx):
        if torch.is_tensor(idx):
            idx = idx.tolist()

        voxel = self.data[idx]["voxel"]
        label = self.class_map[self.data[idx]["label"]]

        #return sample
        return (voxel, label)

data = dataset.load_data(["ADNI2"])
data_set = BrainData(data, CLASS_MAP)

n_train = int(len(data_set) * 0.8)
n_val = int(len(data_set) - n_train)

torch.manual_seed(0)

train_dataset, val_dataset = torch.utils.data.random_split(data_set, [n_train, n_val])

train_loader = torch.utils.data.DataLoader(
    train_dataset, batch_size=64, shuffle=True, num_workers=5)

val_loader = torch.utils.data.DataLoader(
        val_dataset, batch_size=64, shuffle=False, num_workers=5)

# set data loader
train_loader = torch.utils.data.DataLoader(
      dataset=train_dataset,
      batch_size=64, 
      shuffle=True,
      num_workers=5)

val_loader = torch.utils.data.DataLoader(
      dataset=val_dataset,
      batch_size=64, 
      shuffle=False,
      num_workers=5)

#class AlexNet
class AlexNet(nn.Module):

    def __init__(self, num_classes):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv3d(3, 64, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv3d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv3d(192, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv3d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv3d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2),
        )
        self.classifier = nn.Sequential(
            nn.Dropout(),
            nn.Linear(256 * 4 * 4, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, num_classes),
        )

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size(0), 256 * 4 * 4)
        x = self.classifier(x)
        return x

# select device
num_classes = 5
device = 'cuda' if torch.cuda.is_available() else 'cpu'
net = AlexNet(num_classes).to(device)

# optimizing
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.01, momentum=0.9, weight_decay=5e-4)

# training
num_epochs = 20
train_loss_list, train_acc_list, val_loss_list, val_acc_list = [], [], [], []

### training
for epoch in range(num_epochs):
    train_loss, train_acc, val_loss, val_acc = 0, 0, 0, 0

    # ====== train_mode ======
    net.train()
    for i, (images, labels) in enumerate(train_loader):
      images, labels = images.to(device), labels.to(device)      
      optimizer.zero_grad()
      outputs = net(images)
      loss = criterion(outputs, labels)
      train_loss += loss.item()
      train_acc += (outputs.max(1)[1] == labels).sum().item()
      loss.backward()
      optimizer.step()

    avg_train_loss = train_loss / len(train_loader.dataset)
    avg_train_acc = train_acc / len(train_loader.dataset)

    # ====== val_mode ======
    net.eval()
    with torch.no_grad():
      for images, labels in val_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = net(images)
        loss = criterion(outputs, labels)
        val_loss += loss.item()
        val_acc += (outputs.max(1)[1] == labels).sum().item()
    avg_val_loss = val_loss / len(val_loader.dataset)
    avg_val_acc = val_acc / len(val_loader.dataset)

    print ('Epoch [{}/{}], Loss: {loss:.4f}, val_loss: {val_loss:.4f}, val_acc: {val_acc:.4f}' 
                   .format(epoch+1, num_epochs, i+1, loss=avg_train_loss, val_loss=avg_val_loss, val_acc=avg_val_acc))
    train_loss_list.append(avg_train_loss)
    train_acc_list.append(avg_train_acc)
    val_loss_list.append(avg_val_loss)
    val_acc_list.append(avg_val_acc)


# plot graph
plt.figure()
plt.plot(range(num_epochs), train_loss_list, color='blue', linestyle='-', label='train_loss')
plt.plot(range(num_epochs), val_loss_list, color='green', linestyle='--', label='val_loss')
plt.legend()
plt.xlabel('epoch')
plt.ylabel('loss')
plt.title('Training and validation loss')
plt.grid()
plt.show()

plt.figure()
plt.plot(range(num_epochs), train_acc_list, color='blue', linestyle='-', label='train_acc')
plt.plot(range(num_epochs), val_acc_list, color='green', linestyle='--', label='val_acc')
plt.legend()
plt.xlabel('epoch')
plt.ylabel('acc')
plt.title('Training and validation accuracy')
plt.grid()
plt.show()