pytorch 学习笔记（三）

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, ))])     #将图像变量转化为张量，并将0到255的数值压缩到（0,1）的正态分布上
train_dataset = datasets.MNIST(root='C:/Users/王莫莫/Desktop/计算机视觉系列课程-资料/mnist/',train=True,download=True,transform=transform)
train_loader = DataLoader(train_dataset,shuffle=True,batch_size=batch_size)
test_dataset = datasets.MNIST(root='C:/Users/王莫莫/Desktop/计算机视觉系列课程-资料/mnist/',train=False,download=True,transform=transform)
test_loader = DataLoader(test_dataset,shuffle=False,batch_size=batch_size)

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)                               #view函数（-1）表示根据另外一个数来自动调整维度，如果这里只有一个维度，就会将x里面的所有维度数据转化成一维的，并且按先后顺序排列。
        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 = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs,target = data
        optimizer.zero_grad()
        # forward + backward + update
        outputs = model(inputs)
        loss = criterion(outputs,target)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
        if batch_idx % 300 == 299:           #300代更新一次迭代,loss也重新开始计算
            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():                               #torch.no_grad表示后续的程序不进行梯度计算
        for data in test_loader:
            images,labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)            #dim有0,1两个值，0表示按行搜索，1表示按列搜索，torch.max返回搜索数据的最大值与下标，我们这里predicted代表的是返回的下标
            total += labels.size(0)                                  #data数据的标签，每读入一次，total总数增加
            correct += (predicted == labels).sum().item()			 #如果是仅包含一个元素的tensor，可以使用.item()来得到对应的python数值
            print('Accuracy on test set: %d %%' % (100 * correct / total))

if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        if epoch  == 9:
            test()