LeNet试验（一） 搭建pytorch版模型及运行

  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 np

import 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*400
        x = 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 x

    def 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_size
        size = x.size()[1:]  
        num_features = 1
        for s in size:
            num_features *= s
        return num_features 

   
#训练函数
def train(epoch):
    #调用前向传播
    model.train()     
    train_loss = 0
    for 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 = 0
    correct = 0
    for 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 = X
            self.y_data = y
        elif mode=='test':
            self.x_data = Xt
            self.y_data = yt
        self.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, target

    def __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: