mnist数据集训练_Part 06 在MNIST数据集上执行联邦学习训练CNN模型

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms

import syft as sy  # <-- NEW: import the Pysyft library
hook = sy.TorchHook(torch)  # <-- NEW: hook PyTorch ie add extra functionalities to support Federated Learning
bob = sy.VirtualWorker(hook, id="bob")  # <-- NEW: define remote worker bob
alice = sy.VirtualWorker(hook, id="alice")  # <-- NEW: and alice

class Arguments():
    def __init__(self):
        self.batch_size = 64
        self.test_batch_size = 1000
        self.epochs = 10
        self.lr = 0.01
        self.momentum = 0.5
        self.no_cuda = False
        self.seed = 1
        self.log_interval = 30
        self.save_model = False
 
args = Arguments()
 
use_cuda = not args.no_cuda and torch.cuda.is_available()
 
torch.manual_seed(args.seed)
 
device = torch.device("cuda" if use_cuda else "cpu")
 
kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}

federated_train_loader = sy.FederatedDataLoader(
        datasets.MNIST('../data', train=True, download=True, transform=transforms.Compose([
            transforms.ToTensor(),
            transforms.Normalize((0.1307,),(0.3081,)) # 这是ImageNet数据集的方差和均值
        ])).federate((bob, alice)), # 将数据集分发到所有的指定节点，现在是联邦数据集了
        batch_size=args.batch_size, shuffle=True, **kwargs)

test_loader = torch.utils.data.DataLoader(
    datasets.MNIST('../data', train=False, transform=transforms.Compose([
                       transforms.ToTensor(),
                       transforms.Normalize((0.1307,), (0.3081,))
                   ])),
    batch_size=args.test_batch_size, shuffle=True, **kwargs)

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5, 1)
        self.conv2 = nn.Conv2d(20, 50, 5, 1)
        self.fc1 = nn.Linear(4*4*50, 500)
        self.fc2 = nn.Linear(500, 10)
 
    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = F.max_pool2d(x, 2, 2)
        x = F.relu(self.conv2(x))
        x = F.max_pool2d(x, 2, 2)
        x = x.view(-1, 4*4*50)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)
net = Net()
print(net)
'''
Net(
  (conv1): Conv2d(1, 20, kernel_size=(5, 5), stride=(1, 1))
  (conv2): Conv2d(20, 50, kernel_size=(5, 5), stride=(1, 1))
  (fc1): Linear(in_features=800, out_features=500, bias=True)
  (fc2): Linear(in_features=500, out_features=10, bias=True)
)
'''

def train(args, model, device, federated_train_loader, optimizer, epoch):
    model.train() # 设置模型为训练模式
    for batch_index, (data, target) in enumerate(federated_train_loader):
        model.send(data.location)
        data, target = data.to(device), target.to(device) # 如果有GPU搬到GPU计算
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward() # 计算梯度
        optimizer.step() # 更新参数
        model.get() # 取回模型
        if batch_index % args.log_interval == 0:
            loss = loss.get() # 每隔一段时间取回loss看看
            print('Train Epoch: {} [{}/{} ({:.0f}%)]tLoss: {:.6f}'.format(
                epoch, batch_idx * args.batch_size, len(federated_train_loader) * args.batch_size,
                100. * batch_idx / len(federated_train_loader), loss.item()))
```

def test(args, model, device, test_loader):
    model.eval() # 设置模型为评估模式
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction='sum').item() # sum up batch loss
            pred = output.argmax(1, keepdim=True) # get the index of the max log-probability 
            correct += pred.eq(target.view_as(pred)).sum().item()
 
    test_loss /= len(test_loader.dataset)
 
    print('nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))

%%time
model = Net().to(device)
optimizer = optim.SGD(model.parameters(), lr=args.lr) # TODO momentum is not supported at the moment
 
for epoch in range(1, args.epochs + 1):
    train(args, model, device, federated_train_loader, optimizer, epoch)
    test(args, model, device, test_loader)
 
if (args.save_model):
    torch.save(model.state_dict(), "mnist_cnn.pt")

Train Epoch: 4 [59520/60032 (99%)]	Loss: 0.057204
Test set: Average loss: 0.0534, Accuracy: 9828/10000 (98%)
 
Train Epoch: 5 [0/60032 (0%)]	Loss: 0.161142
Train Epoch: 5 [1920/60032 (3%)] Loss: 0.031823

Train Epoch: 4 [56320/60000 (94%)]	Loss: 0.029797
Train Epoch: 4 [56960/60000 (95%)]	Loss: 0.016238
Train Epoch: 4 [57600/60000 (96%)]	Loss: 0.090854
Train Epoch: 4 [58240/60000 (97%)]	Loss: 0.088320
Train Epoch: 4 [58880/60000 (98%)]	Loss: 0.097426
Train Epoch: 4 [59520/60000 (99%)]	Loss: 0.006990
 
Test set: Average loss: 0.0348, Accuracy: 9897/10000 (99%)