LeNet非常简单，在MNIST数据集运行速度很快，所以开辟LeNet试验系列文章，以试验各种语句、技巧的效果，分析神经网络的一些特性。

1，Pytorch版本LeNet代码

  数据路径为’minst/’，文件夹内放置minst集中的四个gz文件，代码文件放在文件夹外面。

import gzip, struct import numpy as npimport torch from torch import nn from torch.nn import functional as F from torch.utils.data import Dataset, DataLoader#读取数据的函数 def _read(image, label):minist_dir = 'mnist/'with gzip.open(minist_dir + label) as flbl:magic, num = struct.unpack(">II", flbl.read(8))label = np.fromstring(flbl.read(), dtype=np.int8)with gzip.open(minist_dir + image, 'rb') as fimg:magic, num, rows, cols = struct.unpack(">IIII", fimg.read(16))image = np.fromstring(fimg.read(), dtype=np.uint8).reshape(len(label), rows, cols)return image, label #读取数据 def get_data():train_img, train_label = _read('train-images-idx3-ubyte.gz','train-labels-idx1-ubyte.gz')test_img, test_label = _read('t10k-images-idx3-ubyte.gz','t10k-labels-idx1-ubyte.gz')return [train_img, train_label, test_img, test_label]#定义lenet5 class LeNet5(nn.Module):def __init__(self):'''构造函数，定义网络的结构'''super().__init__()#定义卷积层self.conv1 = nn.Conv2d(1, 6, 5, padding=2)#第二个卷积层，6个输入，16个输出，5*5的卷积filter self.conv2 = nn.Conv2d(6, 16, 5)#最后是三个全连接层self.fc1 = nn.Linear(16*5*5, 120)self.fc2 = nn.Linear(120, 84)self.fc3 = nn.Linear(84, 10)def forward(self, x):'''前向传播函数'''#先卷积，然后调用relu激活函数，再最大值池化操作x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))#第二次卷积+池化操作x = F.max_pool2d(F.relu(self.conv2(x)), (2, 2))#重新塑形,将多维数据重新塑造为二维数据，256*400x = x.view(-1, self.num_flat_features(x))#print('size', x.size())#第一个全连接x = F.relu(self.fc1(x))x = F.relu(self.fc2(x))x = self.fc3(x)return xdef num_flat_features(self, x):#x.size()返回值为(256, 16, 5, 5)，size的值为(16, 5, 5)，256是batch_sizesize = x.size()[1:] num_features = 1for s in size:num_features *= sreturn num_features #训练函数 def train(epoch):#调用前向传播model.train() train_loss = 0for batch_idx, (data, target) in enumerate(train_loader):if use_gpu:data, target = data.cuda(), target.cuda()optimizer.zero_grad()output = model(data)loss = criterion(output, target)loss.backward()optimizer.step()train_loss += loss.item()train_loss /= len(train_loader.dataset)print('Train Epoch: {} \tTrain Loss: {:.6f}'.format(epoch, train_loss))#定义测试函数 def test():model.eval() #测试模式，主要是保证dropout和BN和训练过程一致。test_loss = 0correct = 0for data, target in test_loader:if use_gpu:data, target = data.cuda(), target.cuda()output = model(data)#计算总的损失test_loss += criterion(output, target).item()pred = output.data.max(1, keepdim=True)[1] #获得得分最高的类别correct += pred.eq(target.data.view_as(pred)).cpu().sum()test_loss /= len(test_loader.dataset)print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.2f}%)\n'.format(test_loss, correct, len(test_loader.dataset),100. * correct / len(test_loader.dataset)))class DealDataset(Dataset):"""数据封装成dataset类型"""def __init__(self,mode='train'):X, y, Xt, yt = get_data()if mode=='train':self.x_data = Xself.y_data = yelif mode=='test':self.x_data = Xtself.y_data = ytself.x_data = torch.from_numpy(self.x_data.reshape(-1, 1, 28, 28)).float()self.y_data = torch.from_numpy(self.y_data).long()self.len = self.x_data.shape[0]def __getitem__(self, index):data = self.x_data[index]target = self.y_data[index]return data, targetdef __len__(self):return self.len#封装数据集 train_dataset = DealDataset(mode='train') test_dataset = DealDataset(mode='test') #定义数据加载器 kwargs = {"num_workers": 0, "pin_memory": True} train_loader = DataLoader(dataset=train_dataset, shuffle=True, batch_size=256, **kwargs) test_loader = DataLoader(dataset=test_dataset, shuffle=True, batch_size=256, **kwargs)#实例化网络 model = LeNet5() #是否使用GPU use_gpu = torch.cuda.is_available() if use_gpu:model = model.cuda()print('USE GPU') else:print('USE CPU') #使用交叉熵损失函数 criterion = nn.CrossEntropyLoss(size_average=False) #优化器 optimizer = torch.optim.Adam(model.parameters(), lr=0.001, betas=(0.9, 0.99))#执行训练和测试 for epoch in range(1, 101):train(epoch)test()

2，运行

运行结果：

下面几个画图的代码上面没有。
train_loss:

test_loss:

accuarcy:

总结

以上是生活随笔为你收集整理的LeNet试验（一） 搭建pytorch版模型及运行的全部内容，希望文章能够帮你解决所遇到的问题。

如果觉得生活随笔网站内容还不错，欢迎将生活随笔推荐给好友。