import torch
from torchvision import transforms,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,))
])

# 訓(xùn)練集
train_dataset = datasets.MNIST(root='G:/datasets/mnist',train=True,download=False,transform=transform)
train_loader = DataLoader(train_dataset,shuffle=True,batch_size=batch_size)
# 測試集
test_dataset = datasets.MNIST(root='G:/datasets/mnist',train=False,download=False,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)
? ? ? ? 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()
# 模型加載到GPU上
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

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.to(device))
? ? ? ? loss = criterion(outputs, target.to(device))
? ? ? ? loss.backward()
? ? ? ? optimizer.step()

? ? ? ? running_loss += loss.item()
? ? ? ? if batch_idx % 300 == 299:
? ? ? ? ? ? print('[%d,%d] 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.to(device))
? ? ? ? ? ? _, predicted = torch.max(outputs.data, dim=1)
? ? ? ? ? ? total += labels.size(0)
? ? ? ? ? ? correct += (predicted.cpu() == labels).sum().item()
? ? print('Accuracy on test set: %d %%' % (100 * correct / total))

for epoch in range(10):
? ? train(epoch)
? ? test()