train_vgg19.py

import argparse
import os
import shutil
import time
import math

import torch
import torch.nn as nn
import torch.nn.parallel
import torch.backends.cudnn as cudnn
import torch.optim
import torch.utils.data
import torchvision.transforms as transforms
import torchvision.datasets as datasets

class VGG(nn.Module):
    '''
    VGG model
    '''
    def __init__(self, features):
        super(VGG, self).__init__()
        self.features = features
        self.classifier = nn.Sequential(
            nn.Dropout(),
            nn.Linear(512, 512),
            nn.ReLU(True),
            nn.Dropout(),
            nn.Linear(512, 512),
            nn.ReLU(True),
            nn.Linear(512, 10),
        )
         # Initialize weights
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
                m.bias.data.zero_()

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size(0), -1)
        x = self.classifier(x)
        return x

def make_layers(cfg, batch_norm=False):
    layers = []
    in_channels = 3
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    return nn.Sequential(*layers)

def vgg19():
    """VGG 19-layer model (configuration "E")"""
    return VGG(make_layers([64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M',
          512, 512, 512, 512, 'M']))

parser = argparse.ArgumentParser(description='PyTorch ImageNet Training')
parser.add_argument('-j', '--workers', default=4, type=int, metavar='N',
                    help='number of data loading workers (default: 4)')
parser.add_argument('--epochs', default=300, type=int, metavar='N',
                    help='number of total epochs to run')
parser.add_argument('--start-epoch', default=0, type=int, metavar='N',
                    help='manual epoch number (useful on restarts)')
parser.add_argument('-b', '--batch-size', default=128, type=int,
                    metavar='N', help='mini-batch size (default: 128)')
parser.add_argument('--lr', '--learning-rate', default=0.05, type=float,
                    metavar='LR', help='initial learning rate')
parser.add_argument('--momentum', default=0.9, type=float, metavar='M',
                    help='momentum')
parser.add_argument('--weight-decay', '--wd', default=5e-4, type=float,
                    metavar='W', help='weight decay (default: 5e-4)')
parser.add_argument('--print-freq', '-p', default=20, type=int,
                    metavar='N', help='print frequency (default: 20)')
parser.add_argument('--resume', default='', type=str, metavar='PATH',
                    help='path to latest checkpoint (default: none)')
parser.add_argument('-e', '--evaluate', dest='evaluate', action='store_true',
                    help='evaluate model on validation set')
parser.add_argument('--pretrained', dest='pretrained', action='store_true',
                    help='use pre-trained model')
parser.add_argument('--cpu', dest='cpu', action='store_true',
                    help='use cpu')
parser.add_argument('--save_dir', dest='save_dir',
                    help='The directory used to save the trained models',
                    default='./vgg19model/', type=str)
parser.add_argument('--real_dir', type=str, default='./cifardata/')#this is the folder for real images

best_prec1 = 0


def main():
    global args, best_prec1
    args = parser.parse_args()

    # Check the save_dir exists or not
    if not os.path.exists(args.save_dir):
        os.makedirs(args.save_dir)

    if not os.path.exists(args.real_dir):
        os.makedirs(args.real_dir)

    model = vgg19()

    model.features = torch.nn.DataParallel(model.features)
    if args.cpu:
        model.cpu()
    else:
        model.cuda()

    # optionally resume from a checkpoint
    if args.resume:
        if os.path.isfile(args.resume):
            print("=> loading checkpoint '{}'".format(args.resume))
            checkpoint = torch.load(args.resume)
            args.start_epoch = checkpoint['epoch']
            best_prec1 = checkpoint['best_prec1']
            model.load_state_dict(checkpoint['state_dict'])
            print("=> loaded checkpoint '{}' (epoch {})"
                  .format(args.evaluate, checkpoint['epoch']))
        else:
            print("=> no checkpoint found at '{}'".format(args.resume))

    cudnn.benchmark = True

    normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                     std=[0.229, 0.224, 0.225])

    train_loader = torch.utils.data.DataLoader(
        datasets.CIFAR10(root=args.real_dir, train=True, transform=transforms.Compose([
            transforms.RandomHorizontalFlip(),
            transforms.RandomCrop(32, 4),
            transforms.ToTensor(),
            normalize,
        ]), download=True),
        batch_size=args.batch_size, shuffle=True,
        num_workers=args.workers, pin_memory=True)

    val_loader = torch.utils.data.DataLoader(
        datasets.CIFAR10(root=args.real_dir, train=False, transform=transforms.Compose([
            transforms.ToTensor(),
            normalize,
        ])),
        batch_size=args.batch_size, shuffle=False,
        num_workers=args.workers, pin_memory=True)

    # define loss function (criterion) and pptimizer
    criterion = nn.CrossEntropyLoss()
    if args.cpu:
        criterion = criterion.cpu()
    else:
        criterion = criterion.cuda()

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

    if args.evaluate:
        validate(val_loader, model, criterion)
        return

    for epoch in range(args.start_epoch, args.epochs):
        adjust_learning_rate(optimizer, epoch)

        # train for one epoch
        train(train_loader, model, criterion, optimizer, epoch)

        # evaluate on validation set
        prec1 = validate(val_loader, model, criterion)

        # remember best prec@1 and save checkpoint
        is_best = prec1 > best_prec1
        best_prec1 = max(prec1, best_prec1)

        if is_best:
            save_checkpoint({
                'epoch': epoch + 1,
                'state_dict': model.state_dict(),
                'best_prec1': best_prec1,
            }, is_best, filename=os.path.join(args.save_dir, 'model_best.pth.tar'))
        else:
            save_checkpoint({
                'epoch': epoch + 1,
                'state_dict': model.state_dict(),
                'best_prec1': best_prec1,
            }, is_best, filename=os.path.join(args.save_dir, 'checkpoint_{}.tar'.format(epoch)))


def train(train_loader, model, criterion, optimizer, epoch):
    """
        Run one train epoch
    """
    batch_time = AverageMeter()
    data_time = AverageMeter()
    losses = AverageMeter()
    top1 = AverageMeter()

    # switch to train mode
    model.train()

    end = time.time()
    for i, (input, target) in enumerate(train_loader):

        # measure data loading time
        data_time.update(time.time() - end)

        if args.cpu == False:
            input = input.cuda()
            target = target.cuda()

        # compute output
        output = model(input)
        loss = criterion(output, target)

        # compute gradient and do SGD step
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        output = output.float()
        loss = loss.float()
        # measure accuracy and record loss
        prec1 = accuracy(output.data, target)[0]
        losses.update(loss.item(), input.size(0))
        top1.update(prec1.item(), input.size(0))

        # measure elapsed time
        batch_time.update(time.time() - end)
        end = time.time()

        if i % args.print_freq == 0:
            print('Epoch: [{0}][{1}/{2}]\t'
                  'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
                  'Data {data_time.val:.3f} ({data_time.avg:.3f})\t'
                  'Loss {loss.val:.4f} ({loss.avg:.4f})\t'
                  'Prec@1 {top1.val:.3f} ({top1.avg:.3f})'.format(
                      epoch, i, len(train_loader), batch_time=batch_time,
                      data_time=data_time, loss=losses, top1=top1))


def validate(val_loader, model, criterion):
    """
    Run evaluation
    """
    batch_time = AverageMeter()
    losses = AverageMeter()
    top1 = AverageMeter()

    # switch to evaluate mode
    model.eval()

    end = time.time()
    for i, (input, target) in enumerate(val_loader):
        if args.cpu == False:
            input = input.cuda()
            target = target.cuda()

        # compute output
        with torch.no_grad():
            output = model(input)
            loss = criterion(output, target)

        output = output.float()
        loss = loss.float()

        # measure accuracy and record loss
        prec1 = accuracy(output.data, target)[0]
        losses.update(loss.item(), input.size(0))
        top1.update(prec1.item(), input.size(0))

        # measure elapsed time
        batch_time.update(time.time() - end)
        end = time.time()

        if i % args.print_freq == 0:
            print('Test: [{0}/{1}]\t'
                  'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
                  'Loss {loss.val:.4f} ({loss.avg:.4f})\t'
                  'Prec@1 {top1.val:.3f} ({top1.avg:.3f})'.format(
                      i, len(val_loader), batch_time=batch_time, loss=losses,
                      top1=top1))

    print(' * Prec@1 {top1.avg:.3f}'
          .format(top1=top1))

    return top1.avg

def save_checkpoint(state, is_best, filename='checkpoint.pth.tar'):
    """
    Save the training model
    """
    torch.save(state, filename)

class AverageMeter(object):
    """Computes and stores the average and current value"""
    def __init__(self):
        self.reset()

    def reset(self):
        self.val = 0
        self.avg = 0
        self.sum = 0
        self.count = 0

    def update(self, val, n=1):
        self.val = val
        self.sum += val * n
        self.count += n
        self.avg = self.sum / self.count


def adjust_learning_rate(optimizer, epoch):
    """Sets the learning rate to the initial LR decayed by 2 every 30 epochs"""
    lr = args.lr * (0.5 ** (epoch // 30))
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr


def accuracy(output, target, topk=(1,)):
    """Computes the precision@k for the specified values of k"""
    maxk = max(topk)
    batch_size = target.size(0)

    _, pred = output.topk(maxk, 1, True, True)
    pred = pred.t()
    correct = pred.eq(target.view(1, -1).expand_as(pred))

    res = []
    for k in topk:
        correct_k = correct[:k].view(-1).float().sum(0)
        res.append(correct_k.mul_(100.0 / batch_size))
    return res


if __name__ == '__main__':
    main()