深度学习笔记 —— 样式迁移

直观地理解就是滤镜

目的是训练这样一张图片X，使得该图片放进和内容图片同样一个CNN的时候在某一层的输出能够匹配上内容；同理，X和样式图片进入同一个CNN，某些层的输出在样式上能够匹配。如果能够同时满足这两个条件，那么X既保留了内容，也保留了样式。

import torch
import torchvision
from torch import nn
from d2l import torch as d2l
import matplotlib.pyplot as plt


# 阅读内容和样式图像
d2l.set_figsize()
content_img = d2l.Image.open('./img/rainier.jpg')
d2l.plt.imshow(content_img)
plt.show()

style_img = d2l.Image.open('./img/autumn-oak.jpg')
d2l.plt.imshow(style_img)
plt.show()


# 预处理和后处理
rgb_mean = torch.tensor([0.485, 0.456, 0.406])
rgb_std = torch.tensor([0.229, 0.224, 0.225])


# 图片变成能够训练的tensor
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)


# tensor变回到图片
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)
# 既想要局部的样式，又想要全局的样式，此处内容上不需要过于还原，允许做一定的变形
style_layers, content_layers = [0, 5, 10, 19, 28], [25]
# 28层之后的丢掉
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(style_img, image_shape).to(device)
    _, styles_Y = extract_features(style_X, content_layers, style_layers)
    return style_X, styles_Y


# 定义损失函数
def content_loss(Y_hat, Y):
    # 均方误差
    return torch.square(Y_hat - Y.detach()).mean()


'''
每个通道里面像素的统计信息，和通道之间的统计信息，就是我们的样式
'''


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()


# 每个像素与上下左右像素之间的绝对值不要差太多，使得整个图片比较平均，不要有太多噪点
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())


# 风格转移的损失函数是内容损失、风格损失和总变化损失的加权和
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（对风格损失额外乘了10）
    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 = d2l.Animator(xlabel='epoch', ylabel='loss',
                            xlim=[10, num_epochs],
                            legend=['content', 'style', 'TV'],
                            ncols=2, figsize=(7, 2.5))
    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)])
    return X


device, image_shape = d2l.try_gpu(), (300, 450)
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)
plt.show()