图像风格迁移python代码

以下是一个基于PyTorch实现的图像风格迁移的Python代码示例：

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision.transforms as transforms
import torchvision.models as models
from PIL import Image
import matplotlib.pyplot as plt

# 定义图像处理函数
loader = transforms.Compose([
    transforms.Resize((512, 512)),  # 调整图像大小
    transforms.ToTensor()  # 转换为张量
])

unloader = transforms.ToPILImage()  # 将张量转换为图像


# 定义图像加载函数
def image_loader(image_name):
    image = Image.open(image_name)
    image = loader(image).unsqueeze(0)
    return image.to(device, torch.float)


# 定义模型
class ContentLoss(nn.Module):
    def __init__(self, target):
        super(ContentLoss, self).__init__()
        self.target = target.detach()

    def forward(self, input):
        self.loss = nn.functional.mse_loss(input, self.target)
        return input


class StyleLoss(nn.Module):
    def __init__(self, target_feature):
        super(StyleLoss, self).__init__()
        self.target = gram_matrix(target_feature).detach()

    def forward(self, input):
        G = gram_matrix(input)
        self.loss = nn.functional.mse_loss(G, self.target)
        return input


def gram_matrix(input):
    a, b, c, d = input.size()
    features = input.view(a * b, c * d)
    G = torch.mm(features, features.t())
    return G.div(a * b * c * d)


class Normalization(nn.Module):
    def __init__(self, mean, std):
        super(Normalization, self).__init__()
        self.mean = torch.tensor(mean).view(-1, 1, 1)
        self.std = torch.tensor(std).view(-1, 1, 1)

    def forward(self, img):
        return (img - self.mean) / self.std


# 定义模型
class StyleTransferModel(nn.Module):
    def __init__(self, content_img, style_img, cnn=models.vgg19(pretrained=True).features.to(device).eval(),
                 content_layers=['conv_4'], style_layers=['conv_1', 'conv_2', 'conv_3', 'conv_4', 'conv_5']):
        super(StyleTransferModel, self).__init__()
        self.content_layers = content_layers
        self.style_layers = style_layers
        self.content_losses = []
        self.style_losses = []
        self.model = nn.Sequential(Normalization([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]))
        i = 0
        for layer in cnn.children():
            if isinstance(layer, nn.Conv2d):
                i += 1
                name = 'conv_{}'.format(i)
            elif isinstance(layer, nn.ReLU):
                name = 'relu_{}'.format(i)
                layer = nn.ReLU(inplace=False)
            elif isinstance(layer, nn.MaxPool2d):
                name = 'pool_{}'.format(i)
            elif isinstance(layer, nn.BatchNorm2d):
                name = 'bn_{}'.format(i)
            else:
                raise RuntimeError('Unrecognized layer: {}'.format(layer.__class__.__name__))
            self.model.add_module(name, layer)

            if name in content_layers:
                target = self.model(content_img).detach()
                content_loss = ContentLoss(target)
                self.model.add_module("content_loss_{}".format(i), content_loss)
                self.content_losses.append(content_loss)

            if name in style_layers:
                target_feature = self.model(style_img).detach()
                style_loss = StyleLoss(target_feature)
                self.model.add_module("style_loss_{}".format(i), style_loss)
                self.style_losses.append(style_loss)

        for i in range(len(self.model) - 1, -1, -1):
            if isinstance(self.model[i], ContentLoss) or isinstance(self.model[i], StyleLoss):
                break
        self.model = self.model[:(i + 1)]

    def forward(self, x):
        return self.model(x)


# 定义图像风格迁移函数
def style_transfer(content_img_path, style_img_path, num_steps=300,
                   style_weight=100000, content_weight=1):
    content_img = image_loader(content_img_path)
    style_img = image_loader(style_img_path)
    input_img = content_img.clone()
    optimizer = optim.LBFGS([input_img.requires_grad_()])

    model = StyleTransferModel(content_img, style_img).to(device)

    print('Start style transfer...')
    run = [0]
    while run[0] <= num_steps:

        def closure():
            input_img.data.clamp_(0, 1)
            optimizer.zero_grad()
            model(input_img)
            style_score = 0
            content_score = 0

            for sl in model.style_losses:
                style_score += sl.loss
            for cl in model.content_losses:
                content_score += cl.loss

            style_score *= style_weight
            content_score *= content_weight

            loss = style_score + content_score
            loss.backward()

            run[0] += 1
            if run[0] % 50 == 0:
                print("run {}:".format(run))
                print('Style Loss : {:4f} Content Loss: {:4f}'.format(
                    style_score.item(), content_score.item()))
                print()

            return style_score + content_score

        optimizer.step(closure)

    input_img.data.clamp_(0, 1)
    return input_img


# 定义图像显示函数
def imshow(tensor, title=None):
    image = tensor.cpu().clone()
    image = image.squeeze(0)
    image = unloader(image)
    plt.imshow(image)
    if title is not None:
        plt.title(title)
    plt.pause(0.001)


# 设置设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# 运行图像风格迁移
output = style_transfer('content.jpg', 'style.jpg')

# 显示结果
plt.figure()
imshow(output, title='Output Image')

# 保存结果
output_img = unloader(output.cpu().clone().squeeze(0))
output_img.save('output.jpg')