题外话

用MNIST数据集来进行模型学习的通用代码：

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

#Dataset&Dataloader必备
batch_size = 64
#pillow（PIL）读的原图像格式为W*H*C，原值较大
# 转为格式为C*W*H值为0-1的Tensor
transform = transforms.Compose([
    #变为格式为C*W*H的Tensor
    transforms.ToTensor(),
    #第一个是均值，第二个是标准差，变值为0-1
    transforms.Normalize((0.1307, ), (0.3081, ))
])

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

train_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(test_dataset, shuffle=False, batch_size=bacth_size)


class Net(torch.nn.Module):
    def __init__(self):
        #根据实际情况自己写

    def forward(self, x):
        ##根据初试函数写
    
model = Net()
#交叉熵损失
criterion = torch.nn.CrossEntropyLoss()
#随机梯度下降，momentum表冲量，在更新时一定程度上保留原方向
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
#这里还可以选择是否要用GPU跑模型
#用显卡来算，就是把模型迁移到GPU上去
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
#通过这句话改跑模型的设备
model.to(device)

def train(epoch):
    running_loss = 0.0
    #提取数据
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        #用GPU要加这句：inputs, target = inputs.to(device), target.to(device)
        #优化器清零
        optimizer.zero_grad()
        #前馈+反馈+更新
        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()
        #累计loss
        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
    #避免计算梯度
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            #GPU就加：images, labels = images.to(device), labels.to(device)
            outputs = model(images)
            #取每一行（dim=1表第一个维度）最大值（max）的下标(predicted)及最大值(_)
            _, predicted = torch.max(outputs.data, dim=1)
            #加上这一个批量的总数（batch_size），label的形式为[N,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()