visual_style_transfer.py

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

from PIL import Image
import torchvision.transforms as transforms
import torchvision.models as models
import copy

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
imsize = 512 if torch.cuda.is_available() else 128

loader = transforms.Compose([
    transforms.Resize((imsize, imsize)),
    transforms.ToTensor()
])
unloader = transforms.ToPILImage()

def image_loader(image):
    image = loader(image).unsqueeze(0)
    return image.to(device, torch.float)

def imshow(tensor):
    image = tensor.cpu().clone()
    image = image.squeeze(0)
    image = unloader(image)
    return image

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

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 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 = F.mse_loss(G, self.target)
        return input

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).to(device)
        self.std = torch.tensor(std).view(-1, 1, 1).to(device)
    def forward(self, img):
        return (img - self.mean) / self.std

content_layers_default = ['conv_4']
style_layers_default = ['conv_1', 'conv_2', 'conv_3', 'conv_4', 'conv_5']

def get_style_model_and_losses(cnn, normalization_mean, normalization_std,
                               style_img, content_img,
                               content_layers=content_layers_default,
                               style_layers=style_layers_default):
    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 = f'conv_{i}'
        elif isinstance(layer, nn.ReLU):
            name = f'relu_{i}'
            layer = nn.ReLU(inplace=False)
        elif isinstance(layer, nn.MaxPool2d):
            name = f'pool_{i}'
        elif isinstance(layer, nn.BatchNorm2d):
            name = f'bn_{i}'
        else:
            raise RuntimeError(f'Unrecognized layer: {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(f"content_loss_{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(f"style_loss_{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

def get_input_optimizer(input_img):
    return optim.LBFGS([input_img.requires_grad_()])

def run_style_transfer(content_img, style_img, num_steps=300,
                       style_weight=1000000, content_weight=1):
    input_img = content_img.clone()
    model, style_losses, content_losses = get_style_model_and_losses(
        cnn, cnn_normalization_mean, cnn_normalization_std,
        style_img, content_img
    )
    optimizer = get_input_optimizer(input_img)

    run = [0]
    while run[0] <= num_steps:
        def closure():
            input_img.data.clamp_(0, 1)
            optimizer.zero_grad()
            model(input_img)
            style_score = sum(sl.loss for sl in style_losses)
            content_score = sum(cl.loss for cl in content_losses)

            style_score *= style_weight
            content_score *= content_weight

            loss = style_score + content_score
            loss.backward()

            run[0] += 1
            return loss

        optimizer.step(closure)

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