PyTorch搭建AlexNet

PyTorch搭建AlexNet

Alexnet是2012年Imagenet竞赛的冠军模型，准确率达到了57.1%, top-5识别率达到80.2%。

AlexNet网络结构图

结构详细解读

AlexNet网络由8层构成，包括5层卷积层和3层全连接层。输入为3x224x224。

各部分网络结构的参数及输入输出图像大小计算。

层数	input size	kernel size	filters	stride	padding	output size	max pooling（kernel = 3, stride = 2)
1	3x224x224	11x11	96	4	2	96x55x55	Yes
2	96x27x27	5x5	256	1	2	256x27x27	Yes
3	256x13x13	3x3	384	1	1	384x13x13	No
4	384x13x13	3x3	384	1	1	384x13x13	No
5	384x13x13	3x3	256	1	1	256x13x13	Yes

PyTorch搭建

import torch
import torch.nn as nn
import torchvision

class AlexNet(nn.Module):
    def __init__(self,num_classes=1000):
        super(AlexNet,self).__init__()
        self.feature_extraction = nn.Sequential(
            nn.Conv2d(in_channels=3,out_channels=96,kernel_size=11,stride=4,padding=2,bias=False),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3,stride=2,padding=0),
            nn.Conv2d(in_channels=96,out_channels=192,kernel_size=5,stride=1,padding=2,bias=False),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3,stride=2,padding=0),
            nn.Conv2d(in_channels=192,out_channels=384,kernel_size=3,stride=1,padding=1,bias=False),
            nn.ReLU(inplace=True),
            nn.Conv2d(in_channels=384,out_channels=256,kernel_size=3,stride=1,padding=1,bias=False),
            nn.ReLU(inplace=True),
            nn.Conv2d(in_channels=256,out_channels=256,kernel_size=3,stride=1,padding=1,bias=False),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2, padding=0),
        )
        self.classifier = nn.Sequential(
            nn.Dropout(p=0.5),
            nn.Linear(in_features=256*6*6,out_features=4096),
            nn.ReLU(inplace=True),
            nn.Dropout(p=0.5),
            nn.Linear(in_features=4096, out_features=4096),
            nn.ReLU(inplace=True),
            nn.Linear(in_features=4096, out_features=num_classes),
        )
    def forward(self,x):
        x = self.feature_extraction(x)
        x = x.view(x.size(0),256*6*6)
        x = self.classifier(x)
        return x


if __name__ =='__main__':
    # model = torchvision.models.AlexNet()
    model = AlexNet()
    print(model)

    input = torch.randn(8,3,224,224)
    out = model(input)
    print(out.shape)