1. 程式人生 > >pytorch---之mnist

pytorch---之mnist

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
from torch.autograd import Variable

# 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()
args.cuda = not args.no_cuda and torch.cuda.is_available()

torch.manual_seed(args.seed) #為CPU設定種子用於生成隨機數,以使得結果是確定的
if args.cuda:
    torch.cuda.manual_seed(args.seed)#為當前GPU設定隨機種子;如果使用多個GPU,應該使用torch.cuda.manual_seed_all()為所有的GPU設定種子。


kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
"""載入資料。組合資料集和取樣器,提供資料上的單或多程序迭代器
引數:
dataset:Dataset型別,從其中載入資料
batch_size:int,可選。每個batch載入多少樣本
shuffle:bool,可選。為True時表示每個epoch都對資料進行洗牌
sampler:Sampler,可選。從資料集中取樣樣本的方法。
num_workers:int,可選。載入資料時使用多少子程序。預設值為0,表示在主程序中載入資料。
collate_fn:callable,可選。
pin_memory:bool,可選
drop_last:bool,可選。True表示如果最後剩下不完全的batch,丟棄。False表示不丟棄。
"""
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.batch_size, shuffle=True, **kwargs)


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)#輸入和輸出通道數分別為1和10
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)#輸入和輸出通道數分別為10和20
        self.conv2_drop = nn.Dropout2d()#隨機選擇輸入的通道,將其設為0
        self.fc1 = nn.Linear(320, 50)#輸入的向量大小和輸出的大小分別為320和50
        self.fc2 = nn.Linear(50, 10)

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

model = Net()
if args.cuda:
    model.cuda()#將所有的模型引數移動到GPU上

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

def train(epoch):
    model.train()#把module設成training模式,對Dropout和BatchNorm有影響
    for batch_idx, (data, target) in enumerate(train_loader):
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data), Variable(target)#Variable類對Tensor物件進行封裝,會儲存該張量對應的梯度,以及對生成該張量的函式grad_fn的一個引用。如果該張量是使用者建立的,grad_fn是None,稱這樣的Variable為葉子Variable。
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)#負log似然損失
        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.data[0]))

def test(epoch):
    model.eval()#把module設定為評估模式,只對Dropout和BatchNorm模組有影響
    test_loss = 0
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        test_loss += F.nll_loss(output, target).data[0]#Variable.data
        pred = output.data.max(1)[1] # get the index of the max log-probability
        correct += pred.eq(target.data).cpu().sum()

    test_loss = test_loss
    test_loss /= len(test_loader) # loss function already averages over batch size
    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, args.epochs + 1):
    train(epoch)
    test(epoch)

---------------------

本文來自 CodeTutor 的CSDN 部落格 ,全文地址請點選:https://blog.csdn.net/victoriaw/article/details/72354307?utm_source=copy