動手學深度學習PyTorch版-數據增強

數據增強

圖像增廣

import os
os.listdir("/home/kesci/input/img2083/")

%matplotlib inline
import os
import time
import torch
from torch import nn, optim
from torch.utils.data import Dataset, DataLoader
import torchvision
import sys
from PIL import Image

sys.path.append("/home/kesci/input/")
#置當前使用的GPU設備僅爲0號設備
os.environ["CUDA_VISIBLE_DEVICES"] = "0"   

import d2lzh1981 as d2l

# 定義device，是否使用GPU，依據計算機配置自動會選擇
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(torch.__version__)
print(device)

常用增廣方法

d2l.set_figsize()
img = Image.open('/home/kesci/input/img2083/img/cat1.jpg')
d2l.plt.imshow(img)

# 本函數已保存在d2lzh_pytorch包中方便以後使用
def show_images(imgs, num_rows, num_cols, scale=2):
    figsize = (num_cols * scale, num_rows * scale)
    _, axes = d2l.plt.subplots(num_rows, num_cols, figsize=figsize)
    for i in range(num_rows):
        for j in range(num_cols):
            axes[i][j].imshow(imgs[i * num_cols + j])
            axes[i][j].axes.get_xaxis().set_visible(False)
            axes[i][j].axes.get_yaxis().set_visible(False)
    return axes

def apply(img, aug, num_rows=2, num_cols=4, scale=1.5):
    Y = [aug(img) for _ in range(num_rows * num_cols)]
    show_images(Y, num_rows, num_cols, scale)

翻轉和裁剪

apply(img, torchvision.transforms.RandomHorizontalFlip())
apply(img, torchvision.transforms.RandomVerticalFlip())
shape_aug = torchvision.transforms.RandomResizedCrop(200, scale=(0.1, 1), ratio=(0.5, 2))
apply(img, shape_aug)

變化顏色

apply(img, torchvision.transforms.ColorJitter(brightness=0.5, contrast=0, saturation=0, hue=0))
apply(img, torchvision.transforms.ColorJitter(brightness=0, contrast=0, saturation=0, hue=0.5))
apply(img, torchvision.transforms.ColorJitter(brightness=0, contrast=0.5, 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)

多圖像增廣方法

augs = torchvision.transforms.Compose([
    torchvision.transforms.RandomHorizontalFlip(), color_aug, shape_aug])
apply(img, augs)

使用圖像增廣訓練模型

CIFAR_ROOT_PATH = '/home/kesci/input/cifar102021'
all_imges = torchvision.datasets.CIFAR10(train=True, root=CIFAR_ROOT_PATH, download = True)
# all_imges的每一個元素都是(image, label)
show_images([all_imges[i][0] for i in range(32)], 4, 8, scale=0.8);

flip_aug = torchvision.transforms.Compose([
     torchvision.transforms.RandomHorizontalFlip(),
     torchvision.transforms.ToTensor()])

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

num_workers = 0 if sys.platform.startswith('win32') else 4
def load_cifar10(is_train, augs, batch_size, root=CIFAR_ROOT_PATH):
    dataset = torchvision.datasets.CIFAR10(root=root, train=is_train, transform=augs, download=False)
    return DataLoader(dataset, batch_size=batch_size, shuffle=is_train, num_workers=num_workers)

增廣訓練模型

# 本函數已保存在d2lzh_pytorch包中方便以後使用
def train(train_iter, test_iter, net, loss, optimizer, device, num_epochs):
    net = net.to(device)
    print("training on ", device)
    batch_count = 0
    for epoch in range(num_epochs):
        train_l_sum, train_acc_sum, n, start = 0.0, 0.0, 0, time.time()
        for X, y in train_iter:
            X = X.to(device)
            y = y.to(device)
            y_hat = net(X)
            l = loss(y_hat, y)
            optimizer.zero_grad()
            l.backward()
            optimizer.step()
            train_l_sum += l.cpu().item()
            train_acc_sum += (y_hat.argmax(dim=1) == y).sum().cpu().item()
            n += y.shape[0]
            batch_count += 1
        test_acc = d2l.evaluate_accuracy(test_iter, net)
        print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f, time %.1f sec'
              % (epoch + 1, train_l_sum / batch_count, train_acc_sum / n, test_acc, time.time() - start))

def train_with_data_aug(train_augs, test_augs, lr=0.001):
    batch_size, net = 256, d2l.resnet18(10)
    optimizer = torch.optim.Adam(net.parameters(), lr=lr)
    loss = torch.nn.CrossEntropyLoss()
    train_iter = load_cifar10(True, train_augs, batch_size)
    test_iter = load_cifar10(False, test_augs, batch_size)
    train(train_iter, test_iter, net, loss, optimizer, device, num_epochs=10)

train_with_data_aug(flip_aug, no_aug)