pytorch 入门学习多分类问题

pytorch 入门学习多分类问题

运行结果

 [1,  300] loss: 2.287
 [1,  600] loss: 2.137
 [1,  900] loss: 1.192
Accuracy on test set: 78 % 
 [2,  300] loss: 0.560
 [2,  600] loss: 0.422
 [2,  900] loss: 0.361
Accuracy on test set: 90 % 
 [3,  300] loss: 0.307
 [3,  600] loss: 0.292
 [3,  900] loss: 0.258
Accuracy on test set: 93 % 
 [4,  300] loss: 0.228
 [4,  600] loss: 0.221
 [4,  900] loss: 0.201
Accuracy on test set: 94 % 
 [5,  300] loss: 0.178
 [5,  600] loss: 0.178
 [5,  900] loss: 0.158
Accuracy on test set: 95 % 
 [6,  300] loss: 0.141
 [6,  600] loss: 0.139
 [6,  900] loss: 0.144
Accuracy on test set: 96 % 
 [7,  300] loss: 0.129
 [7,  600] loss: 0.116
 [7,  900] loss: 0.114
Accuracy on test set: 96 % 
 [8,  300] loss: 0.107
 [8,  600] loss: 0.100
 [8,  900] loss: 0.106
Accuracy on test set: 96 % 
 [9,  300] loss: 0.091
 [9,  600] loss: 0.088
 [9,  900] loss: 0.089
Accuracy on test set: 96 % 
 [10,  300] loss: 0.079
 [10,  600] loss: 0.074
 [10,  900] loss: 0.080
Accuracy on test set: 96 % 

Process finished with exit code 0

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


#step1 准备数据集

batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.137,),(0.3081,))
])

train_dataset = datasets.MNIST(root='../dataset/mnist',
                               train=True,
                               download=True,
                               transform=transform)

train_loder = DataLoader(train_dataset,
                         shuffle=True,
                         batch_size=batch_size)

test_dataset = datasets.MNIST(root='../dataset/mnist',
                               train=False,
                               download=True,
                               transform=transform)

test_loder = DataLoader(test_dataset,
                        shuffle=False,
                        batch_size=batch_size)

#step2 搭建网络
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.l1 = torch.nn.Linear(784,512)
        self.l2 = torch.nn.Linear(512,256)
        self.l3 = torch.nn.Linear(256,128)
        self.l4 = torch.nn.Linear(128,64)
        self.l5 = torch.nn.Linear(64,10)

    def forward(self,x):
        x = x.view(-1,784)
        x = F.relu(self.l1(x))
        x = F.relu(self.l2(x))
        x = F.relu(self.l3(x))
        x = F.relu(self.l4(x))
        return self.l5(x)

model = Net()

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


#step3 训练
def train(epoch):
    running_loss = 0.0
    for batch_idx,data in enumerate(train_loder,0):
        inputs,target = data
        optimizer.zero_grad()    #梯度清零

        #forward + backward + update
        outputs = model(inputs)
        loss = criterion(outputs,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():      #不计算梯度
        for data in test_loder:
            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()