LeNet（pytorch实现

LeNet

本文编写了一个简单易懂的LeNet网络，并在F-MNIST数据集上进行测试，允许使用GPU计算

在这里插入代码片
import torch
from torch import nn, optim 
import d2lzh_pytorch as d2l

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# f-mnist 数据集是28*28的
class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(1, 6, 5),  # 输出通道，输出通道，核大小
            nn.Sigmoid(),
            nn.MaxPool2d(2, 2),  # 高宽减半
            nn.Conv2d(6, 16, 5),
            nn.Sigmoid(),
            nn.MaxPool2d(2, 2)
        )

        self.fc = nn.Sequential(
            d2l.FlattenLayer(),
            nn.Linear(16*4*4, 120),
            nn.Sigmoid(),
            nn.Linear(120, 84),
            nn.Sigmoid(),
            nn.Linear(84, 10)
        )

    def forward(self, img):
        feature = self.conv(img)
        output = self.fc(feature)
        return output
net = LeNet()

# 数据集
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

# 评估测试集，支持GPU
def evaluate_acc(data_iter, net, device = None):
    if device is None and isinstance(net, nn.Module):
        device = list(net.parameters())[0].device  # 看参数的gpu还是cpu
    acc_sum, n = 0.0, 0
    with torch.no_grad():
        for X,y in data_iter:
            if isinstance(net, nn.Module):  # 这个可加可不加
                net.eval()  # 评估模式
                acc_sum += (net(X.to(device)).argmax(dim=1) == y.to(device)).float().sum().cpu().item()
                net.train()  # 转回训练模式
                n += y.shape[0]
                
    return acc_sum / n

def train(net, train_iter, test_iter, optimizer, device, epochs):
    net = net.to(device)
    loss = nn.CrossEntropyLoss()
    for epoch in range(epochs):
        train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
        for X,y in train_iter:
            X = X.to(device)
            y = y.to(device)
            y_hat = net(X)
            l = loss(y_hat, y)
            optimizer.zero_grad()
            l.backward()
            optimizer.step()
            train_l_sum += l.cpu().item()
            train_acc_sum += (y_hat.argmax(dim=1) == y).sum().cpu().item()
            n += y.shape[0]
        test_acc = evaluate_acc(test_iter, net)
        print('epoch %d, loss %.4f, train_acc %.4f, test_acc %.4f'%(epoch + 1, train_l_sum, train_acc_sum/n, test_acc))

lr, epochs = 0.001, 5
optimizer = torch.optim.Adam(net.parameters(), lr=lr)
train(net, train_iter, test_iter, optimizer, device, epochs)