mixup嵌入到当前模型中，降低过拟合

mixup论文传送门
论文中对比了$\alpha$和$\lambda$在cifar10和cifar100下不同模型的表现，有兴趣的童鞋可以详细看看。作为模型嵌入来说，直接加入以下代码即可实现数据增强mixup手段。

def mixup_data(x, y, alpha=1.0, use_cuda=True):

    '''Compute the mixup data. Return mixed inputs, pairs of targets, and lambda'''
    if alpha > 0.:
        lam = np.random.beta(alpha, alpha)
    else:
        lam = 1.
    batch_size = x.size()[0]
    if use_cuda:
        index = torch.randperm(batch_size).cuda()
    else:
        index = torch.randperm(batch_size)

    mixed_x = lam * x + (1 - lam) * x[index,:]
    y_a, y_b = y, y[index]
    return mixed_x, y_a, y_b, lam

def mixup_criterion(y_a, y_b, lam):
    return lambda criterion, pred: lam * criterion(pred, y_a) + (1 - lam) * criterion(pred, y_b)

def train(trainloader, model, criterion, optimizer, epoch, args):
    # switch to train mode
    model.train()
    batch_time = AverageMeter()
    data_time = AverageMeter()
    losses = AverageMeter()
    top1 = AverageMeter()
    top5 = AverageMeter()
    end = time.time()

    # bar = Bar('Processing', max=len(trainloader))
    for batch_idx, (inputs, targets) in enumerate(trainloader):
        # measure data loading time
        data_time.update(time.time() - end)
        # print(inputs.size())
        if args.use_cuda:
            # inputs, targets = inputs.cuda(), targets.cuda(async=True)
            inputs, targets = inputs.cuda(), targets.cuda()
        # inputs, targets = torch.autograd.Variable(
        #     inputs, requires_grad=False), torch.autograd.Variable(
        #     targets, requires_grad=False)
        if args.is_mixup:
            # generate mixed inputs, two one-hot label vectors and mixing coefficient
            # targets_a is origin_inputs label, argets_b is shuffled origin_inputs label
            inputs, targets_a, targets_b, lam = mixup_data(inputs, targets, args.alpha, args.use_cuda)
            # optimizer.zero_grad()
            outputs = model(inputs)

            loss_func = mixup_criterion(targets_a, targets_b, lam)
            loss = loss_func(criterion, outputs)

只有在训练时输入的样本是两个随机样本的混合，计算损失为两个样本一起计算。有不同的权重值。
我的理解是两个样本的随机混合，效果是能够产生更多数据分布的样本。过拟合另外一方面是测试的样本，训练时没有学习到。那如果在训练期间就尽可能多的产生数据分布的样本，那不就能一定程度降低过拟合了。
进行模型测试为正常样本输入，不进行混合。