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 d2ldevice = 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cpuacc_sum, n = 0.0, 0with 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 / ndef 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, 0for 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)