Pytorch 多分类问题

#########################################full connection###########################################
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,))
    #mean,Std
])
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=True,
                         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()
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:
            print('[%d,%5d] loss: %.3f' % (epoch + 1, batch_idx +1, running_loss / 300))
            running_loss = 0.0

def test():
    correct = 0
    total = 0
    # 不计算梯度
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            #max,index of max
            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()
===============================================================================================================================================

[1, 300] loss: 2.204

1654784it [00:44, 43276.74it/s][1, 600] loss: 0.904
[1, 900] loss: 0.420
Accuracy on test set: 90 %
[2, 300] loss: 0.305
[2, 600] loss: 0.263
[2, 900] loss: 0.222
Accuracy on test set: 93 %
[3, 300] loss: 0.183
[3, 600] loss: 0.168
[3, 900] loss: 0.148
Accuracy on test set: 95 %
[4, 300] loss: 0.132
[4, 600] loss: 0.118
[4, 900] loss: 0.116
Accuracy on test set: 96 %
[5, 300] loss: 0.097
[5, 600] loss: 0.095
[5, 900] loss: 0.092
Accuracy on test set: 96 %
[6, 300] loss: 0.074
[6, 600] loss: 0.079
[6, 900] loss: 0.078
Accuracy on test set: 97 %
[7, 300] loss: 0.065
[7, 600] loss: 0.061
[7, 900] loss: 0.061
Accuracy on test set: 97 %
[8, 300] loss: 0.050
[8, 600] loss: 0.050
[8, 900] loss: 0.052
Accuracy on test set: 97 %
[9, 300] loss: 0.038
[9, 600] loss: 0.047
[9, 900] loss: 0.041
Accuracy on test set: 97 %
[10, 300] loss: 0.031
[10, 600] loss: 0.038
[10, 900] loss: 0.034
Accuracy on test set: 97 %

9920512it [09:12, 17950.01it/s]
1654784it [05:37, 4904.61it/s]

Process finished with exit code 0

#####################################CNN##############################################

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,))
    #mean,Std
])
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=True,
                         batch_size=batch_size)


class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)
        self.pooling = torch.nn.MaxPool2d(2)
        self.fc = torch.nn.Linear(320, 10)

    def forward(self, x):
        # Flatten data from (n, 1, 28, 28) to (n, 784)
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        x = x.view(batch_size, -1) # flatten
        x = self.fc(x)
        return 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:
            print('[%d,%5d] loss: %.3f' % (epoch + 1, batch_idx +1, running_loss / 300))
            running_loss = 0.0

def test():
    correct = 0
    total = 0
    # 不计算梯度
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            #max,index of max
            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()
====================================================================================

[1, 300] loss: 0.720
[1, 600] loss: 0.181
[1, 900] loss: 0.128
Accuracy on test set: 96 %
[2, 300] loss: 0.108
[2, 600] loss: 0.098
[2, 900] loss: 0.088
Accuracy on test set: 97 %
[3, 300] loss: 0.076
[3, 600] loss: 0.079
[3, 900] loss: 0.071
Accuracy on test set: 98 %
[4, 300] loss: 0.066
[4, 600] loss: 0.063
[4, 900] loss: 0.062
Accuracy on test set: 98 %
[5, 300] loss: 0.060
[5, 600] loss: 0.052
[5, 900] loss: 0.055
Accuracy on test set: 98 %
[6, 300] loss: 0.051
[6, 600] loss: 0.050
[6, 900] loss: 0.050
Accuracy on test set: 98 %
[7, 300] loss: 0.045
[7, 600] loss: 0.047
[7, 900] loss: 0.049
Accuracy on test set: 98 %
[8, 300] loss: 0.044
[8, 600] loss: 0.043
[8, 900] loss: 0.041
Accuracy on test set: 98 %
[9, 300] loss: 0.038
[9, 600] loss: 0.038
[9, 900] loss: 0.045
Accuracy on test set: 98 %
[10, 300] loss: 0.037
[10, 600] loss: 0.037
[10, 900] loss: 0.043
Accuracy on test set: 98 %

Process finished with exit code 0