PyTorch 深度学习：多分类问题

解决过程:

1. 准备数据集
2. 设计模型
3. 构造损失函数和优化器
4. 训练和测试

1.准备数据集：

        MNIST里面的数据是PIL  image,所以需要把它转换为PyTorch里面的张量形式。我们都进来的图像张量一般都是(W,H,C),而PyTorch的一般格式是(C,H,W)(C为通道数，H为高，W为宽)，(W,H,C)-->(C,H,W)。采用transforms.ToTensor()方法。
        MNIST数据集里面的值处于0~255之间，为了更好地进行模型的训练，我们对其采用归一化处理，使其值处于0~1内。采用transforms.Normalize()方法。

transform =  transforms.Compose([transforms.ToTensor(),
                                transforms.Normalize((0.1307,),(0.3081))])


train_dataset = datasets.MNIST(root = '../dataset/mnist',
                               train = True,
                               download = True, 
                               transform = transform)
trian_loader = DataLoader(train_dataset,
                          shuffle = True, 
                          batch_size = batch_size)
test_dataset = datasets.MNIST(root = '../dataset/mnist',
                               train = False,
                               download = True, 
                               transform = transform)
test_loader = DataLoader(train_dataset,
                          shuffle = True, 
                          batch_size = batch_size)

2.设计模型

        因为我们之前把数据集转换成了PyTorch的数据格式(N,C,H ,W )，但是神经网络的输入要求是一个二维的矩阵，因此我们必须将数据格式(N,C,H ,W )--->(N,C*H*W)，对应代码中的x = x.view(-1,784)

        除了最后一层，其他层我们使用的激活函数为relu()函数

class NET(torch.nn.Module):
    def __init__(self):
        super(NET, self).__init__()
        self.linear1 = torch.nn.Linear(784,512)
        self.linear2 = torch.nn.Linear(512,256)
        self.linear3 = torch.nn.Linear(256,128)
        self.linear4 = torch.nn.Linear(128,64)
        self.linear5 = torch.nn.Linear(64,10)

    def forward(self, x):
        x = x.view(-1,784)
        x = F.relu(self.linear1(x))
        x = F.relu(self.linear2(x))
        x = F.relu(self.linear3(x))
        x = F.relu(self.linear4(x))
        return self.linear5(x)

3.构造损失函数和优化器：

criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(),lr = 0.01,momentum = 0.5)

4.训练和测试

        训练：

def train(epoch):
    running_loss = 0.0
    for batch_idx,data in enumerate(trian_loader,0):
        inputs,target = data 
        optimizer.zero_grad()
        output = model(inputs)
        loss = criterion(output,target)
        loss.backward()
        optimizer.step()


        running_loss += loss.item()
        if(batch_idx % 300 == 299):
            print('[%d %5d] loss: %.3f' %(epoch+1,batch_idx+1,running_loss/300)) 
        running_loss = 0.0

        测试：

def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images,labels = data
            outputs = model(images)
            _,predicted = torch.max(outputs.data,dim = 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print('accuracy on test set %d %% '%(100*correct/total))

源码：

import imp
import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim


batch_size = 64
transform =  transforms.Compose([transforms.ToTensor(),
                                transforms.Normalize((0.1307,),(0.3081))])


train_dataset = datasets.MNIST(root = '../dataset/mnist',
                               train = True,
                               download = True, 
                               transform = transform)
trian_loader = DataLoader(train_dataset,
                          shuffle = True, 
                          batch_size = batch_size)
test_dataset = datasets.MNIST(root = '../dataset/mnist',
                               train = False,
                               download = True, 
                               transform = transform)
test_loader = DataLoader(train_dataset,
                          shuffle = True, 
                          batch_size = batch_size)


class NET(torch.nn.Module):
    def __init__(self):
        super(NET, self).__init__()
        self.linear1 = torch.nn.Linear(784,512)
        self.linear2 = torch.nn.Linear(512,256)
        self.linear3 = torch.nn.Linear(256,128)
        self.linear4 = torch.nn.Linear(128,64)
        self.linear5 = torch.nn.Linear(64,10)

    def forward(self, x):
        x = x.view(-1,784)
        x = F.relu(self.linear1(x))
        x = F.relu(self.linear2(x))
        x = F.relu(self.linear3(x))
        x = F.relu(self.linear4(x))
        return self.linear5(x)

model = NET()

criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(),lr = 0.01,momentum = 0.5)


def train(epoch):
    running_loss = 0.0
    for batch_idx,data in enumerate(trian_loader,0):
        inputs,target = data 
        optimizer.zero_grad()
        output = model(inputs)
        loss = criterion(output,target)
        loss.backward()
        optimizer.step()


        running_loss += loss.item()
        if(batch_idx % 300 == 299):
            print('[%d %5d] loss: %.3f' %(epoch+1,batch_idx+1,running_loss/300)) 
        running_loss = 0.0


def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images,labels = data
            outputs = model(images)
            _,predicted = torch.max(outputs.data,dim = 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print('accuracy on test set %d %% '%(100*correct/total))

if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()