数据增广

数据增强

• 增加一个已有的数据集，使得有更多的多样性
  • 在语言里面加入各种不同的背景噪音
  • 改变图片的颜色和形状
    

使用增强数据训练

• 一般的情况下是做随机的增强，然后生成图片，然后再进行训练
  

常见的增强的方式

• 几十种其他的办法
  

总结

代码实现

%matplotlib inline
import torch
import torchvision
from torch import nn
from d2l import torch as d2l

d2l.set_figsize()
img = d2l.Image.open("/Users/tiger/Desktop/study/机器学习/d2l-zh/pytorch/img/cat1.jpg")
d2l.plt.imshow(img);

# img: 图片，aug：数据增广的方式，
def apply(img, aug, num_rows=2, num_cols=4, scale=1.5):
    Y = [aug(img) for _ in range(num_rows * num_cols)]
    d2l.show_images(Y, num_rows, num_cols, scale=scale)

# 左右翻转图像
apply(img, torchvision.transforms.RandomHorizontalFlip())  # RandomHorizontalFlip()函数的作用就是在水平方向随机的翻转

# 上下翻转
apply(img, torchvision.transforms.RandomVerticalFlip())  # RandomVerticalFlip()函数的作用就是在垂直方向随机翻转

# 随机剪裁
# RandomResizedCrop函数的作用就是随机裁剪一个然后在Resize，参数一：最后的输出大小，参数二：随机裁剪的大小区间，参数三：裁剪的高宽比
shape_aug = torchvision.transforms.RandomResizedCrop(
            (200, 200), scale=(0.1, 1), ratio=(0.5, 2))

apply(img, shape_aug)

# 随机更改图像的亮度
apply(img, torchvision.transforms.ColorJitter(
        brightness=0.5, contrast=0, saturation=0, hue=0))  # 亮度、对比度、饱和度、色调

# 随机更改图像的色调
apply(img, torchvision.transforms.ColorJitter(
        brightness=0, contrast=0, saturation=0, hue=0.5))  # 亮度、对比度、饱和度、色温

# 随机更改图像的亮度（brightness）、对比度（contrast）、饱和度（saturation）和色调（hue）
color_aug = torchvision.transforms.ColorJitter(brightness=0.5, contrast=0.5,
                                               saturation=0.5, hue=0.5)
apply(img, color_aug)

# 结合多种图像增广方法
# Compose
augs = torchvision.transforms.Compose([
    torchvision.transforms.RandomHorizontalFlip(),
    color_aug, shape_aug
])
apply(img, augs)

# 使用图像增广进行训练
all_images = torchvision.datasets.CIFAR10(train=True, root="../data/", download=True)
d2l.show_images([all_images[i][0] for i in range(32)], 4, 8, scale=0.8);

Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to ../data/cifar-10-python.tar.gz


99.9%

# 只是用最简单的随机左右翻转
train_augs = torchvision.transforms.Compose([
    torchvision.transforms.RandomHorizontalFlip(),
    torchvision.transforms.ToTensor()
])

test_augs = torchvision.transforms.Compose([
    torchvision.transforms.ToTensor()
])

# 定义一个辅助函数，以便读取图像和应用图像增广
def load_cifar10(is_train, sugs, batch_size):
    dataset = torchvision.datasets.CIFAR10(
        root="../data/", train=is_train,
        transforms=augs, download=True)
    dataloader = torch.utils.data.DataLoader(dataset, batch_size=batch_size, 
                                            shuffle=is_train, num_workers=0)
    return dataloader

# 定义一个函数使用多GPU对模型进行训练
def train_batch_ch13(net, X, y, loss, trainer, devices):
    if isinstance(X, list):
        X = [x.to(devices[0]) for x in X]
    else:
        X = X.to(devices[0])
    y = y.to(devices[0])
    net.train()
    trainer.zero_grad()
    pred = net(X)
    l = loss(pred, y)
    l.sum().backward()
    trainer.step()
    train_loss_sum = l.sum()
    train_acc_sum = d2l.accuracy(pred, y)
    return train_loss_sum, train_acc_sum

def train_ch13(net, train_iter, test_iter, loss, trainer, num_epochs,
               devices=d2l.try_all_gpus()):
    timer, num_batches = d2l.Timer(), len(train_iter)
    animator = d2l.Animator(xlabel='epoch', xlim=[1, num_epochs], ylim=[0, 1],
                            legend=['train loss', 'train acc', 'test acc'])
    net = nn.DataParallel(net, device_ids=devices).to(devices[0])
    for epoch in range(num_epochs):
        metric = d2l.Accumulator(4)
        for i, (features, labels) in enumerate(train_iter):
            timer.start()
            l, acc = train_batch_ch13(net, features, labels, loss, trainer,
                                      devices)
            metric.add(l, acc, labels.shape[0], labels.numel())
            timer.stop()
            if (i + 1) % (num_batches // 5) == 0 or i == num_batches - 1:
                animator.add(
                    epoch + (i + 1) / num_batches,
                    (metric[0] / metric[2], metric[1] / metric[3], None))
        test_acc = d2l.evaluate_accuracy_gpu(net, test_iter)
        animator.add(epoch + 1, (None, None, test_acc))
    print(f'loss {metric[0] / metric[2]:.3f}, train acc '
          f'{metric[1] / metric[3]:.3f}, test acc {test_acc:.3f}')
    print(f'{metric[2] * num_epochs / timer.sum():.1f} examples/sec on '
          f'{str(devices)}')

# 定义train_with_data_aug 函数，使用图像增广来训练模型
batch_size, devices, net = 256, d2l.try_all_gpus(), d2l.resnet18(10, 3)

def init_weights(m):
    if type(m) in [nn.Linear, nn.Conv2d]:
        nn.init.xavier_uniform_(m.weight)

net.apply(init_weights)

def train_with_data_aug(train_augs, test_augs, net, lr=0.001):
    train_iter = load_cifar10(True, train_augs, batch_size)
    test_iter = load_cifar10(False, test_augs, batch_size)
    loss = nn.CrossEntropyLoss(reduction="none")
    trainer = torch.optim.Adam(net.parameters(), lr=lr)  # Adam可以理解为一个平滑的SGD
    train_ch13(net, train_iter, test_iter, loss, trainer, 10, devices)

train_with_data_aug(train_augs, test_augs, net)