PyTorch之七—MNIST 手写数字识别_batch_size=512 #大概需要2g的显存

本节基于MNIST数据集，实现CNN学习过程。
这里我们可以先查看图像

import os

import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt

torch.manual_seed(1)  # reproducible

EPOCH = 8
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = False

# 下载数据集
if not (os.path.exists('./mnist/')) or not os.listdir('./mnist/'):
    DOWNLOAD_MNIST = True

train_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=True,
    # 将一张图片或numpy数组转成 (C x H x W)torch.FloatTensor 并归一化[0.0,0.1]
    transform=torchvision.transforms.ToTensor(),
    download=DOWNLOAD_MNIST,
)

print(train_data.train_data.size())    # (60000, 28, 28)
print(train_data.train_labels.size())  # (60000)
plt.imshow(train_data.train_data[1].numpy(), cmap='gray')  # train_data[0]
plt.title('%i' % train_data.train_labels[1])  
plt.show()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33

如下示例，直接运行，数据集自动下载（建议先行下载好数据）

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



# 定义超参数
BATCH_SIZE=512    # 大概需要2G的显存
EPOCHS=20         # 总训练批次
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu") # 让torch判断是否使用GPU


train_loader = torch.utils.data.DataLoader(
        datasets.MNIST('../data', train=True, download=True,
                       transform=transforms.Compose([
                           transforms.ToTensor(),
                           transforms.Normalize((0.1307,), (0.3081,))
                       ])),
        batch_size=BATCH_SIZE, shuffle=True)



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




class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet,self).__init__()      # 1,  28x28
        self.conv1=nn.Conv2d(1,10,5)        # 10, 24x24
        self.conv2=nn.Conv2d(10,20,3)       # 128, 10x10
        self.fc1 = nn.Linear(20*10*10,500)
        self.fc2 = nn.Linear(500,10)

    def forward(self,x):
        in_size = x.size(0)
        out = F.max_pool2d(F.relu(self.conv1(x)), 2, 2)
        out = F.relu(self.conv2(out))
        out = out.view(in_size,-1)
        out = self.fc1(out)
        out = F.relu(out)
        out = self.fc2(out)
        out = F.log_softmax(out,dim=1)
        return out

model = ConvNet().to(DEVICE)
optimizer = optim.Adam(model.parameters())


def train(model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if(batch_idx+1)%30 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'
                  .format(epoch, batch_idx * len(data), len(train_loader.dataset),
                          100. * batch_idx / len(train_loader), loss.item()))

def test(model, device, test_loader):
    model.eval()
    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() # 将一批的损失相加
            pred = output.max(1, keepdim=True)[1]                           # 找到概率最大的下标
            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)))

for epoch in range(1, EPOCHS + 1):
    train(model, DEVICE, train_loader, optimizer, epoch)
    test(model, DEVICE, test_loader)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91

所有操作封装成函数

from __future__ import print_function
import argparse       #Python 命令行解析工具
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)

def train(args, model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        """
        pytorch中CrossEntropyLoss是通过两个步骤计算出来的:
               第一步是计算log softmax，第二步是计算cross entropy（或者说是negative log likehood），
               CrossEntropyLoss不需要在网络的最后一层添加softmax和log层，直接输出全连接层即可。
               
               而NLLLoss则需要在定义网络的时候在最后一层添加log_softmax层(softmax和log层)
               
        总而言之：CrossEntropyLoss() = log_softmax() + NLLLoss() 
        """
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % args.log_interval == 0:
            print('Train_Epoch:{} [{}/{} ({:.2f}%)] \t loss:{:.6f}'
                  .format(epoch,batch_idx*len(data),len(train_loader),
                          100.0*batch_idx/len(train_loader),loss.item()))

def test(args, model, device, test_loader):
    model.eval()
    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, size_average=False).item() # sum up batch loss
            pred = torch.max(output,1)[1]
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)
    print('\n Test_set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'
          .format(test_loss, correct, len(test_loader.dataset),
                  100. * correct / len(test_loader.dataset)))

def main():
    # Training settings
    parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
    parser.add_argument('--batch-size', type=int, default=64, metavar='N',
                        help='input batch size for training (default: 64)')
    parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
                        help='input batch size for testing (default: 1000)')
    parser.add_argument('--epochs', type=int, default=10, metavar='N',
                        help='number of epochs to train (default: 10)')
    parser.add_argument('--lr', type=float, default=0.01, metavar='LR',
                        help='learning rate (default: 0.01)')
    parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
                        help='SGD momentum (default: 0.5)')
    parser.add_argument('--no-cuda', action='store_true', default=False,
                        help='disables CUDA training')
    parser.add_argument('--seed', type=int, default=1, metavar='S',
                        help='random seed (default: 1)')
    parser.add_argument('--log-interval', type=int, default=10, metavar='N',
                        help='how many batches to wait before logging training status')
    args = parser.parse_args()

    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': 2, 'pin_memory': True} if use_cuda else {}
    train_loader = torch.utils.data.DataLoader(
        datasets.MNIST('../data', train=True, download=True,
                       transform=transforms.Compose([
                           transforms.ToTensor(),
                           transforms.Normalize((0.1307,), (0.3081,))
                       ])),
        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)


    model = Net().to(device)
    optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)

    for epoch in range(1, args.epochs + 1):
        train(args, model, device, train_loader, optimizer, epoch)
        test(args, model, device, test_loader)


if __name__ == '__main__':
    main()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117