pytorch task7 手写数字识别

用PyTorch完成手写数字识别

import torch
import torch.utils as utils
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import torch.optim as optim

from torchvision import datasets, transforms

batch_size = 64

train_dataset = datasets.MNIST(root='./data',
                               train=True,
                               transform=transforms.ToTensor(),
                               download=True)

test_dataset = datasets.MNIST(root='./data',
                              train=False,
                              transform=transforms.ToTensor())

train_loader = utils.data.DataLoader(dataset=train_dataset,
                                     batch_size=batch_size,
                                     shuffle=True)

test_loader = utils.data.DataLoader(dataset=test_dataset,
                                    batch_size=batch_size,
                                    shuffle=False)

import matplotlib.pyplot as plt

# % matplotlib inline
for i in range(5):
    plt.figure()
    plt.imshow(train_loader.dataset.train_data[i].numpy())

x = torch.randn(2, 2, 2)
x.view(-1, -1, 4)


class LeNetS(nn.Module):
    def __init__(self):
        super(LeNetS, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, 5, padding=2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = F.max_pool2d(F.tanh(self.conv1(x)), (2, 2))
        x = F.dropout(x, p=0.3, training=self.training)
        x = F.max_pool2d(F.tanh(self.conv2(x), (2, 2)))
        x = F.dropout(x, p=0.3, training=self.training)
        x = x.view(-1, self.num_flat_featrues(x))

        x = F.tanh(self.fc1(x))
        x = F.dropout(x, p=0.3, training=self.training)
        x = F.tanh(self.fc2(x))
        x = F.dropout(x, p=0.3, training=self.training)

        x = self.fc3(x)

    def num_flat_features(self, x):
        size = x.size()[1:]
        num_featrues = 1
        for s in size:
            num_featrues *= s
        return num_featrues


model = LeNetS()

optimizer = optim.SGD(model.parameters(), lr=0.1, momentum=0.9)
criterion = nn.CrossEntropyLoss()

for (data, target) in train_loader:
    for i in range(4):
        plt.figure()
        print(target[i])
        plt.imshow(data[i].numpy[0])

    break


def train(epoch):
    model.train()

    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = Variable(data), Variable(target)
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % 10 == 0:
            Loss.append(loss.data[0])
            print('Train Epoch:{} [{} / {} ({:.0f}%)]\tLoss:{:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                       100. * batch_idx / len(train_loader), loss.data[0]
            ))
        return loss.data[0]


def test():
    model.eval()
    test_loss = 0
    correct = 0

    for data, target in test_loader:
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        test_loss += criterion(output, target).data[0]
        pred = output.data.max(1, keepdim=True)[1]
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()

    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)))


Loss = []
for epoch in range(60):
    loss = train(epoch)
    Loss.append(loss)
    test()