深度学习-李沐-第十三节-常用图像增广方法
图像增广
常用图像增广方法
d2l.set_figsize()
img = d2l.Image.open('../img/cat1.jpg')
d2l.plt.imshow(img);
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)
翻转和裁剪
apply(img, torchvision.transforms.RandomHorizontalFlip())
apply(img, torchvision.transforms.RandomVerticalFlip())
shape_aug = torchvision.transforms.RandomResizedCrop(
(200, 200), scale=(0.1, 1), ratio=(0.5, 2))
apply(img, shape_aug)
改变颜色
apply(img, torchvision.transforms.ColorJitter(brightness=0.5, contrast=0, saturation=0, hue=0))
color_aug = torchvision.transforms.ColorJitter(
brightness=0.5, contrast=0.5, saturation=0.5, hue=0.5)
apply(img, color_aug)
训练
#@save
def train_batch_ch13(net, X, y, loss, trainer, devices):
"""用多GPU进行小批量训练"""
if isinstance(X, list):
# 微调BERT中所需(稍后讨论)
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
#@save
def train_ch13(net, train_iter, test_iter, loss, trainer, num_epochs,
devices=d2l.try_all_gpus()):
"""用多GPU进行模型训练"""
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):
# 4个维度:储存训练损失,训练准确度,实例数,特点数
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)}')
小结
图像增广基于现有的训练数据生成随机图像,来提高模型的泛化能力。
为了在预测过程中得到确切的结果,我们通常对训练样本只进行图像增广,而在预测过程中不使用带随机操作的图像增广。
深度学习框架提供了许多不同的图像增广方法,这些方法可以被同时应用。