[人工智能]pytorch实现深度卷积神经网络（AlexNet）

2012年，AlexNet横空出世。这个模型的名字来源于论文第一作者的姓名Alex Krizhevsky 。AlexNet使用了8层卷积神经网络，并以很大的优势赢得了ImageNet 2012图像识别挑战赛。它首次证明了学习到的特征可以超越手工设计的特征，从而一举打破计算机视觉研究的前状。

import torch
import torchvision
from torch import nn
from torchsummary import summary
print(torch.__version__)

?1.12.1+cpu

class AlexNet(nn.Module):
    def __init__(self):
        super(AlexNet, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(3, 96, 11, 4), # in_channels, out_channels, kernel_size, stride, padding
            nn.ReLU(),
            nn.MaxPool2d(3, 2), # kernel_size, stride
            # 减小卷积窗口，使用填充为2来使得输入与输出的高和宽一致，且增大输出通道数
            nn.Conv2d(96, 256, 5, 1, 2),
            nn.ReLU(),
            nn.MaxPool2d(3, 2),
            # 连续3个卷积层，且使用更小的卷积窗口。除了最后的卷积层外，进一步增大了输出通道数。
            # 前两个卷积层后不使用池化层来减小输入的高和宽
            nn.Conv2d(256, 384, 3, 1, 1),
            nn.ReLU(),
            nn.Conv2d(384, 384, 3, 1, 1),
            nn.ReLU(),
            nn.Conv2d(384, 256, 3, 1, 1),
            nn.ReLU(),
            nn.MaxPool2d(3, 2)
        )
         # 这里全连接层的输出个数比LeNet中的大数倍。使用丢弃层来缓解过拟合
        self.fc = nn.Sequential(
            nn.Linear(256*5*5, 4096),
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.Linear(4096, 4096),
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.Linear(4096, 1000),
        )
    def forward(self, img):
        feature = self.conv(img)
        output = self.fc(feature.view(img.shape[0], -1))
        return output


model = AlexNet()
print(model)

AlexNet(
  (conv): Sequential(
    (0): Conv2d(3, 96, kernel_size=(11, 11), stride=(4, 4))
    (1): ReLU()
    (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
    (3): Conv2d(96, 256, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (4): ReLU()
    (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
    (6): Conv2d(256, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU()
    (8): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (9): ReLU()
    (10): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU()
    (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (fc): Sequential(
    (0): Linear(in_features=6400, out_features=4096, bias=True)
    (1): ReLU()
    (2): Dropout(p=0.5, inplace=False)
    (3): Linear(in_features=4096, out_features=4096, bias=True)
    (4): ReLU()
    (5): Dropout(p=0.5, inplace=False)
    (6): Linear(in_features=4096, out_features=1000, bias=True)
  )
)

summary(model, (3, 224, 224))

?

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1           [-1, 96, 54, 54]          34,944
              ReLU-2           [-1, 96, 54, 54]               0
         MaxPool2d-3           [-1, 96, 26, 26]               0
            Conv2d-4          [-1, 256, 26, 26]         614,656
              ReLU-5          [-1, 256, 26, 26]               0
         MaxPool2d-6          [-1, 256, 12, 12]               0
            Conv2d-7          [-1, 384, 12, 12]         885,120
              ReLU-8          [-1, 384, 12, 12]               0
            Conv2d-9          [-1, 384, 12, 12]       1,327,488
             ReLU-10          [-1, 384, 12, 12]               0
           Conv2d-11          [-1, 256, 12, 12]         884,992
             ReLU-12          [-1, 256, 12, 12]               0
        MaxPool2d-13            [-1, 256, 5, 5]               0
           Linear-14                 [-1, 4096]      26,218,496
             ReLU-15                 [-1, 4096]               0
          Dropout-16                 [-1, 4096]               0
           Linear-17                 [-1, 4096]      16,781,312
             ReLU-18                 [-1, 4096]               0
          Dropout-19                 [-1, 4096]               0
           Linear-20                 [-1, 1000]       4,097,000
================================================================
Total params: 50,844,008
Trainable params: 50,844,008
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 10.18
Params size (MB): 193.95
Estimated Total Size (MB): 204.71
----------------------------------------------------------------