构建多层感知机 (MLP) 网络：图像特征提取

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

class MLP(nn.Module): def init(self): super(MLP, self).init() self.linear1 = nn.Linear(32*32, 2048) self.linear2 = nn.Linear(2048, 512) self.linear3 = nn.Linear(512, 20)

def forward(self, x):
    x = x.view(x.size(0), -1)
    x = self.linear1(x)
    x = F.sigmoid(x)
    x = self.linear2(x)
    x = F.relu(x)
    x = self.linear3(x)
    return x

if name == 'main': net = MLP() # 初始化权重和偏差 for name, param in net.named_parameters(): if 'bias' in name: nn.init.constant_(param, 0.0) elif 'weight' in name: nn.init.uniform_(param, 0.0, 1.0) print(f'{name}'s mean: {param.mean()}') # 使用随机输入进行测试 x = torch.randn(1, 1, 32, 32) out = net(x) print(f'Flatten output shape: {x.view(x.size(0), -1).shape}') print(f'Linear output shape: {net.linear1(out).shape}') print(f'Sigmoid output shape: {net.linear2(F.sigmoid(net.linear1(out))).shape}') print(f'ReLU output shape: {net.linear3(F.relu(net.linear2(F.sigmoid(net.linear1(out))))).shape}') print(f'Linear output shape: {out.shape}')