AlexNet

AlexNet卷积网络，见论文和参考代码。AlexNet成功开启了深度学习在计算机视觉领域的革命，并且为后续的神经网络架构奠定了基础。，其原理大致如下：

#=> AlexNet   - CNN + MLP
#=> input img - (b, c, h, w)  
#=> input y   - (b, )  
feat   = CNN(img) # (b, c_1, h_1, w_1)
logits = MLP(feat.reshape(b, -1)) # (b, n_class)
loss   = cross_entropy(logits, y)

---

import torch
import torch.nn as nn
import torch.nn.functional as F

class AlexNet(nn.Module):
    def __init__(self, ch_in, d_out):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(ch_in, 64, kernel_size=11, stride=4, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            
            nn.Conv2d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            
            nn.Conv2d(192, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
        )
        self.avgpool = nn.AdaptiveAvgPool2d((6, 6))
        self.classifier = nn.Sequential(
            nn.Dropout(0.5),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(0.5),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, d_out)
        )
    
    def forward(self, x):
        x = self.features(x)
        x = self.avgpool(x)
        x = x.view(x.size(0), 256 * 6 * 6)
        logits = self.classifier(x)
        # probas = F.softmax(logits, dim=1)
        prob = F.log_softmax(logits, dim=1)
        return prob
    
if __name__ == "__main__":
    ch_in, d_out = 1, 10
    x = torch.randn(2, 1, 64, 64)
    model = AlexNet(ch_in, d_out)
    y_pred = model(x)
    print(y_pred.shape)