Pytorch之卷積神經網絡（Mnist）學習

Pytorch之Mnist學習

以前寫的代碼太差，而代碼的書寫和可讀性很重要，同時想掌握兩個Deep Learning的框架，在此學習記錄。閱讀的代碼是pytorch官方給的例子：https://github.com/pytorch/examples

1、Argparse庫的使用

Argparse庫的使用很頻繁，一般是寫在開頭，主要是用於命令行（cmd）中運行python文件的一些參數設置（如：batch size， learning rate等）。

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)')

設置了命令行參數，即可以在命令行裏面輸入對應的操作設置。如果在命令行運行時，沒有給出對應的參數，即使用默認參數。
如cd到目標文件的目錄下，可以如下操作，就可以得到所有的設置的參數設置：

python main.py --help

2、數據集

對於一些經典的數據集的獲取方式可以直接採用torchvision.datasets，如Mnist數據集：torchvision.datasets.MNIST。
https://pytorch.org/docs/stable/torchvision/datasets.html?highlight=datasets mnist#torchvision.datasets.MNIST
同時用torch.utils.data.DataLoader進行對數據集進行加載。
https://pytorch.org/docs/stable/data.html?highlight=torch utils data dataloader#torch.utils.data.DataLoader

kwargs = {'num_workers': 1, '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)

其中注意到的細節是：當使用gpu的時候，就用子進程來加載這個數據集（可能需要下載）
同時爲其分配了一定的內存，但是不建議這樣操作，一般就默認設置爲False。https://discuss.pytorch.org/t/what-is-the-disadvantage-of-using-pin-memory/1702
詳細中文解釋：https://blog.csdn.net/u014380165/article/details/79058479

同時另一個細節：transform的配置，也就是圖像的預處理過程，進行了歸一化。
詳細中文解釋：https://www.jianshu.com/p/13e31d619c15

但是歸一化爲什麼mean和std的設置是如此：https://discuss.pytorch.org/t/normalization-in-the-mnist-example/457/6

3、網絡搭建

一般是創建一個class來使用，並且需要將網絡每一層的過程首先定義，並看是否有gpu將網絡放在gpu上。

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

直接使用torch的函數nn.Conv2d（權重在此進行自動初始化了）等等，並且需要繼承nn.Module類。

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)

4、參數更新

因爲繼承了model類，直接通過參數更新。

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

注意到model.train()設置爲訓練，output = model(data)加載數據到之前定義的網絡中，梯度清0，求損失，反向傳播，一步一步的執行。

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)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % args.log_interval == 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()))

5、代碼

from __future__ import print_function
import argparse
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, 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)
    
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)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % args.log_interval == 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(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, reduction='sum').item() # sum up batch loss
            pred = output.argmax(dim=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)))

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')
    
    parser.add_argument('--save-model', action='store_true', default=False,
                        help='For Saving the current Model')
    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': 1, '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 (args.save_model):
        torch.save(model.state_dict(),"mnist_cnn.pt")
        
if __name__ == '__main__':
    main()