Style Transfer

graph LR
    A[Content Image] --> B[Feature Extraction]
    C[Style Image] --> B
    B --> D[Style-Content Fusion]
    D --> E[Image Reconstruction]
    E --> F[Output: Stylized Image]

    style A fill:#f9f,stroke:#333
    style C fill:#f9f,stroke:#333
    style F fill:#f9f,stroke:#333

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

# Device configuration
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Image loading and preprocessing
def image_loader(image_name, imsize):
    loader = transforms.Compose([
        transforms.Resize(imsize),
        transforms.ToTensor()])
    image = Image.open(image_name)
    image = loader(image).unsqueeze(0)
    return image.to(device, torch.float)

# Image unloading (convert tensor to PIL image)
def imshow(tensor, title=None):
    unloader = transforms.ToPILImage()
    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)

# Content and style loss
class ContentLoss(nn.Module):
    def __init__(self, target):
        super(ContentLoss, self).__init__()
        self.target = target.detach()

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

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

    def gram_matrix(self, 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)

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

# Load VGG19 model
cnn = models.vgg19(pretrained=True).features.to(device).eval()
cnn_normalization_mean = torch.tensor([0.485, 0.456, 0.406]).to(device)
cnn_normalization_std = torch.tensor([0.229, 0.224, 0.225]).to(device)

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

# Style transfer function
def get_style_model_and_losses(cnn, normalization_mean, normalization_std,
                              style_img, content_img,
                              content_layers=['conv_4'],
                              style_layers=['conv_1', 'conv_2', 'conv_3', 'conv_4', 'conv_5']):
    cnn = copy.deepcopy(cnn)
    normalization = Normalization(normalization_mean, normalization_std).to(device)

    content_losses = []
    style_losses = []

    model = nn.Sequential(normalization)

    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__))

        model.add_module(name, layer)

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

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

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

    model = model[:(i + 1)]

    return model, style_losses, content_losses

# Run style transfer
def run_style_transfer(cnn, normalization_mean, normalization_std,
                      content_img, style_img, input_img, num_steps=300,
                      style_weight=1000000, content_weight=1):
    print('Building the style transfer model..')
    model, style_losses, content_losses = get_style_model_and_losses(
        cnn, normalization_mean, normalization_std, style_img, content_img)

    input_img.requires_grad_(True)
    model.requires_grad_(False)

    optimizer = optim.LBFGS([input_img])

    print('Optimizing..')
    run = [0]
    while run[0] <= num_steps:

        def closure():
            with torch.no_grad():
                input_img.clamp_(0, 1)

            optimizer.zero_grad()
            model(input_img)
            style_score = 0
            content_score = 0

            for sl in style_losses:
                style_score += sl.loss
            for cl in 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)

    with torch.no_grad():
        input_img.clamp_(0, 1)

    return input_img

# Example usage
if __name__ == "__main__":
    # Load images
    imsize = 512 if torch.cuda.is_available() else 128
    content_img = image_loader("content.jpg", imsize)
    style_img = image_loader("style.jpg", imsize)

    # Create input image (copy of content image)
    input_img = content_img.clone()

    # Run style transfer
    output = run_style_transfer(cnn, cnn_normalization_mean, cnn_normalization_std,
                              content_img, style_img, input_img)

    # Display results
    plt.figure()
    imshow(style_img, title='Style Image')
    plt.figure()
    imshow(content_img, title='Content Image')
    plt.figure()
    imshow(output, title='Output Image')
    plt.ioff()
    plt.show()