In-depth reading of the paper Alexnet

🛠 Tools and Programming
1

Teacher Li Mu does a great job explaining. Let’s combine it with the recent study of CNN’s AlexNet code encapsulation and take a look together.

Up 9年后重读深度学习奠基作之一：AlexNet【论文精读·2】_哔哩哔哩_bilibili
Down AlexNet论文逐段精读【论文精读】_哔哩哔哩_bilibili
Code implementation (after watching both parts, you’ll understand the code with a nod, if you haven’t watched this video) 代码_哔哩哔哩_bilibili

import torch.nn as nn
import torch
from torchsummary import summary

class AlexNet(nn.Module):
    def __init__(self, num_classes=1000, init_weights=False):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 96, kernel_size=11, stride=4, padding=2),  # input[3, 224, 224]  output[96, 55, 55]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[96, 27, 27]

            nn.Conv2d(96, 256, kernel_size=5, padding=2),           # output[256, 27, 27]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[256, 13, 13]

            nn.Conv2d(256, 384, kernel_size=3, padding=1),          # output[384, 13, 13]
            nn.ReLU(inplace=True),

            nn.Conv2d(384, 384, kernel_size=3, padding=1),          # output[384, 13, 13]
            nn.ReLU(inplace=True),

            nn.Conv2d(384, 256, kernel_size=3, padding=1),          # output[256, 13, 13]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[256, 6, 6]
        )
        self.classifier = nn.Sequential(
            nn.Dropout(p=0.5),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),

            nn.Dropout(p=0.5),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            
            nn.Linear(4096, num_classes),
        )
        if init_weights:
            self._initialize_weights()

    def forward(self, x):
        x = self.features(x)
        x = torch.flatten(x, start_dim=1)
        x = self.classifier(x)
        return x

    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.constant_(m.bias, 0)

def alexnet(num_classes): 
    model = AlexNet(num_classes=num_classes)
    return model