使用Pytorch手动搭建Alexnet网络

首先贴一个Alexnet网络结构的示意图

然后按照上图编写Alexnet网络，一一对应即可：

import torch
import torch.nn as nn
#import torchvision

class Alexnet(nn.Module):
    def __init__(self, class_num = 1000):
        super(Alexnet, self).__init__()
        self.featureExtraction = nn.Sequential(
            nn.Conv2d(in_channels= 3, out_channels= 96, kernel_size= 11, stride= 4, bias= 0),
            nn.ReLU(inplace= True),
            nn.MaxPool2d(kernel_size= 3, stride= 2, padding= 0),
            nn.Conv2d(in_channels= 96, out_channels= 256, kernel_size= 5, stride= 1, padding = 2, bias= 0),
            nn.ReLU(inplace= True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(in_channels=256, out_channels=384, kernel_size=3, stride=1, padding=1, bias=0),
            nn.ReLU(inplace=True),
            nn.Conv2d(in_channels=384, out_channels=384, kernel_size= 3, stride=1, padding= 1, bias=0),
            nn.ReLU(inplace=True),
            nn.Conv2d(in_channels=384, out_channels=256, kernel_size= 3, stride= 1, padding= 1, bias=0),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size= 3, stride= 2, padding= 0)
        )
        self.fc = nn.Sequential(
            nn.Dropout(0.5),
            nn.Linear(in_features= 256*6*6, out_features= 4096),
            nn.ReLU(inplace= True),
            nn.Dropout(0.5),
            nn.Linear(in_features= 4096, out_features= 4096),
            nn.ReLU(inplace= True),
            nn.Linear(in_features= 4096, out_features= class_num)
        )

    def forward(self, x):
        x = self.featureExtraction(x)
        x = x.view(x.size(0), 256*6*6)
        x = self.fc(x)
        return x

if __name__ == '__main__':
    model = Alexnet()
    print(model)
    input = torch.randn(8, 3, 227, 227)
    out = model(input)
    print(out.shape)
    print(out)

• 测试结果：

Alexnet(
  (featureExtraction): Sequential(
    (0): Conv2d(3, 96, kernel_size=(11, 11), stride=(4, 4), bias=False)
    (1): ReLU(inplace=True)
    (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), bias=False)
    (4): ReLU(inplace=True)
    (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), bias=False)
    (7): ReLU(inplace=True)
    (8): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
    (9): ReLU(inplace=True)
    (10): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
    (11): ReLU(inplace=True)
    (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (fc): Sequential(
    (0): Dropout(p=0.5, inplace=False)
    (1): Linear(in_features=9216, out_features=4096, bias=True)
    (2): ReLU(inplace=True)
    (3): Dropout(p=0.5, inplace=False)
    (4): Linear(in_features=4096, out_features=4096, bias=True)
    (5): ReLU(inplace=True)
    (6): Linear(in_features=4096, out_features=1000, bias=True)
  )
)
torch.Size([8, 1000])
tensor([[ 7.8992e-03, -5.0696e-03,  1.0371e-02,  ...,  1.2258e-02,
         -1.5194e-05, -1.0831e-02],
        [ 1.6226e-02, -1.3935e-02, -1.0737e-04,  ...,  1.4513e-02,
         -7.0582e-03, -2.1036e-02],
        [-1.6301e-03, -1.3431e-02, -3.7540e-04,  ..., -7.3956e-04,
         -8.8427e-03, -1.8173e-02],
        ...,
        [ 1.6233e-02, -4.9180e-03,  3.8799e-03,  ...,  7.6893e-03,
         -2.4209e-03, -1.8067e-02],
        [ 1.7316e-02, -1.5523e-02,  7.8454e-03,  ...,  9.2318e-03,
         -1.2605e-02, -1.2254e-02],
        [ 2.3515e-02, -1.6916e-02,  1.2861e-02,  ...,  1.5658e-02,
         -8.7848e-03, -2.1918e-02]], grad_fn=<AddmmBackward>)

最后

以上就是懵懂奇异果为你收集整理的使用Pytorch手动搭建Alexnet网络的全部内容，希望文章能够帮你解决使用Pytorch手动搭建Alexnet网络所遇到的程序开发问题。

如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。