深度学习 —— 个人学习笔记21（风格迁移）

声明

  本文章为个人学习使用，版面观感若有不适请谅解，文中知识仅代表个人观点，若出现错误，欢迎各位批评指正。

四十一、风格迁移

import torch
import torchvision
from PIL import Image
from torch import nn
from IPython import display
from matplotlib import pyplot as plt
from matplotlib_inline import backend_inline

def accuracy(y_hat, y):                                                           # 定义一个函数来为预测正确的数量计数
    """计算预测正确的数量"""
    if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
        y_hat = y_hat.argmax(axis=1)
    cmp = y_hat.type(y.dtype) == y                                                # bool 类型，若预测结果与实际结果一致，则为 True
    return float(cmp.type(y.dtype).sum())

def evaluate_accuracy_gpu(net, data_iter, device=None):
    """使用GPU计算模型在数据集上的精度"""
    if isinstance(net, nn.Module):
        net.eval()  # 设置为评估模式
        if not device:
            device = next(iter(net.parameters())).device
    # 正确预测的数量，总预测的数量
    metric = Accumulator(2)
    with torch.no_grad():
        for X, y in data_iter:
            if isinstance(X, list):
                # BERT微调所需的（之后将介绍）
                X = [x.to(device) for x in X]
            else:
                X = X.to(device)
            y = y.to(device)
            metric.add(accuracy(net(X), y), y.numel())
    return metric[0] / metric[1]

def set_axes(axes, xlabel, ylabel, xlim, ylim, xscale, yscale, legend):
    axes.set_xlabel(xlabel), axes.set_ylabel(ylabel)
    axes.set_xscale(xscale), axes.set_yscale(yscale)
    axes.set_xlim(xlim),     axes.set_ylim(ylim)
    if legend:
        axes.legend(legend)
    axes.grid()

class Accumulator:                                                                # 定义一个实用程序类 Accumulator，用于对多个变量进行累加
    """在n个变量上累加"""
    def __init__(self, n):
        self.data = [0.0] * n

    def add(self, *args):
        self.data = [a + float(b) for a, b in zip(self.data, args)]

    def reset(self):
        self.data = [0.0] * len(self.data)

    def __getitem__(self, idx):
        return self.data[idx]

class Animator:                                                                   # 定义一个在动画中绘制数据的实用程序类 Animator
    """在动画中绘制数据"""
    def __init__(self, xlabel=None, ylabel=None, legend=None, xlim=None,
                 ylim=None, xscale='linear', yscale='linear',
                 fmts=('-', 'm--', 'g-.', 'r:'), nrows=1, ncols=1,
                 figsize=(5.5, 3.5), suptitle=None):
        plt.rcParams['font.sans-serif'] = ['Microsoft YaHei']
        # 增量地绘制多条线
        if legend is None:
            legend = []
        backend_inline.set_matplotlib_formats('svg')
        self.fig, self.axes = plt.subplots(nrows, ncols, figsize=figsize)
        plt.suptitle(suptitle)
        if nrows * ncols == 1:
            self.axes = [self.axes, ]
        # 使用lambda函数捕获参数
        self.config_axes = lambda: set_axes(
            self.axes[0], xlabel, ylabel, xlim, ylim, xscale, yscale, legend)
        self.X, self.Y, self.fmts = None, None, fmts

    def add(self, x, y):
        # Add multiple data points into the figure
        if not hasattr(y, "__len__"):
            y = [y]
        n = len(y)
        if not hasattr(x, "__len__"):
            x = [x] * n
        if not self.X:
            self.X = [[] for _ in range(n)]
        if not self.Y:
            self.Y = [[] for _ in range(n)]
        for i, (a, b) in enumerate(zip(x, y)):
            if a is not None and b is not None:
                self.X[i].append(a)
                self.Y[i].append(b)
        self.axes[0].cla()
        for x, y, fmt in zip(self.X, self.Y, self.fmts):
            self.axes[0].plot(x, y, fmt)
        self.config_axes()
        display.display(self.fig)
        # 通过以下两行代码实现了在PyCharm中显示动图
        plt.draw()
        plt.pause(interval=0.001)
        display.clear_output(wait=True)

def try_gpu(i=0):
    if torch.cuda.device_count() >= i + 1:
        return torch.device(f'cuda:{i}')
    return torch.device('cpu')

""" 图片的显示 """
content_img = Image.open('E:\\cat\\cat.jpg')
img_style = Image.open('E:\\cat\\cat_style.jpg')

rgb_mean = torch.tensor([0.485, 0.456, 0.406])
rgb_std = torch.tensor([0.229, 0.224, 0.225])

"""  预处理和后处理 """
def preprocess(img, image_shape):
    transforms = torchvision.transforms.Compose([
        torchvision.transforms.Resize(image_shape),
        torchvision.transforms.ToTensor(),
        torchvision.transforms.Normalize(mean=rgb_mean, std=rgb_std)])
    return transforms(img).unsqueeze(0)

def postprocess(img):
    img = img[0].to(rgb_std.device)
    img = torch.clamp(img.permute(1, 2, 0) * rgb_std + rgb_mean, 0, 1)
    return torchvision.transforms.ToPILImage()(img.permute(2, 0, 1))

""" 抽取图像特征 """
pretrained_net = torchvision.models.vgg19(pretrained=True)

style_layers, content_layers = [0, 5, 10, 19, 28], [25]

net = nn.Sequential(*[pretrained_net.features[i] for i in
                      range(max(content_layers + style_layers) + 1)])

def extract_features(X, content_layers, style_layers):
    contents = []
    styles = []
    for i in range(len(net)):
        X = net[i](X)
        if i in style_layers:
            styles.append(X)
        if i in content_layers:
            contents.append(X)
    return contents, styles

def get_contents(image_shape, device):
    content_X = preprocess(content_img, image_shape).to(device)
    contents_Y, _ = extract_features(content_X, content_layers, style_layers)
    return content_X, contents_Y

def get_styles(image_shape, device):
    style_X = preprocess(img_style, image_shape).to(device)
    _, styles_Y = extract_features(style_X, content_layers, style_layers)
    return style_X, styles_Y

""" 内容损失 """
def content_loss(Y_hat, Y):
    # 从动态计算梯度的树中分离目标：
    # 这是一个规定的值，而不是一个变量。
    return torch.square(Y_hat - Y.detach()).mean()

""" 风格损失 """
def gram(X):
    num_channels, n = X.shape[1], X.numel() // X.shape[1]
    X = X.reshape((num_channels, n))
    return torch.matmul(X, X.T) / (num_channels * n)

def style_loss(Y_hat, gram_Y):
    return torch.square(gram(Y_hat) - gram_Y.detach()).mean()

""" 全变分损失 """
def tv_loss(Y_hat):
    return 0.5 * (torch.abs(Y_hat[:, :, 1:, :] - Y_hat[:, :, :-1, :]).mean() +
                  torch.abs(Y_hat[:, :, :, 1:] - Y_hat[:, :, :, :-1]).mean())

""" 损失函数 """
content_weight, style_weight, tv_weight = 1, 1e3, 10

def compute_loss(X, contents_Y_hat, styles_Y_hat, contents_Y, styles_Y_gram):
    # 分别计算内容损失、风格损失和全变分损失
    contents_l = [content_loss(Y_hat, Y) * content_weight for Y_hat, Y in zip(
        contents_Y_hat, contents_Y)]
    styles_l = [style_loss(Y_hat, Y) * style_weight for Y_hat, Y in zip(
        styles_Y_hat, styles_Y_gram)]
    tv_l = tv_loss(X) * tv_weight
    # 对所有损失求和
    l = sum(10 * styles_l + contents_l + [tv_l])
    return contents_l, styles_l, tv_l, l

""" 初始化合成图像 """
class SynthesizedImage(nn.Module):
    def __init__(self, img_shape, **kwargs):
        super(SynthesizedImage, self).__init__(**kwargs)
        self.weight = nn.Parameter(torch.rand(*img_shape))

    def forward(self):
        return self.weight

def get_inits(X, device, lr, styles_Y):
    gen_img = SynthesizedImage(X.shape).to(device)
    gen_img.weight.data.copy_(X.data)
    trainer = torch.optim.Adam(gen_img.parameters(), lr=lr)
    styles_Y_gram = [gram(Y) for Y in styles_Y]
    return gen_img(), styles_Y_gram, trainer

""" 训练模型 """
def train(X, contents_Y, styles_Y, device, lr, num_epochs, lr_decay_epoch):
    X, styles_Y_gram, trainer = get_inits(X, device, lr, styles_Y)
    scheduler = torch.optim.lr_scheduler.StepLR(trainer, lr_decay_epoch, 0.8)
    animator = Animator(xlabel='epoch', ylabel='loss',
                        xlim=[10, num_epochs],
                        legend=['content', 'style', 'TV'],
                        ncols=4, figsize=(12.5, 5.5), suptitle='风格迁移')
    for epoch in range(num_epochs):
        trainer.zero_grad()
        contents_Y_hat, styles_Y_hat = extract_features(
            X, content_layers, style_layers)
        contents_l, styles_l, tv_l, l = compute_loss(
            X, contents_Y_hat, styles_Y_hat, contents_Y, styles_Y_gram)
        l.backward()
        trainer.step()
        scheduler.step()
        if (epoch + 1) % 10 == 0:
            animator.axes[1].imshow(postprocess(X))
            animator.add(epoch + 1, [float(sum(contents_l)),
                                     float(sum(styles_l)), float(tv_l)])
        animator.axes[1].set_title('迁移后')
        animator.axes[2].set_title('原图')
        animator.axes[2].imshow(content_img)
        animator.axes[3].set_title('风格')
        animator.axes[3].imshow(img_style)
    plt.show()
    return X


device, image_shape = try_gpu(), (500, 500)
net = net.to(device)
content_X, contents_Y = get_contents(image_shape, device)
_, styles_Y = get_styles(image_shape, device)
output = train(content_X, contents_Y, styles_Y, device, 0.3, 500, 50)

---

  文中部分知识参考：B 站 —— 跟李沐学AI；百度百科