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 = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# Define the fixed size
target_size = (512, 512)
loader = transforms.Compose([
transforms.Resize(target_size),
transforms.ToTensor()])
def image_loader(image_name):
image = Image.open(image_name)
image = loader(image).unsqueeze(0)
return image.to(device, torch.float)
style_img = image_loader("style_fanGao.jpg")
content_img = image_loader("Zengbo.jpg")
# Resize the images to the same size
style_img = F.interpolate(style_img, size=target_size, mode='bilinear', align_corners=False)
content_img = F.interpolate(content_img, size=target_size, mode='bilinear', align_corners=False)
assert style_img.size() == content_img.size(), "Style and content images must be of the same size."
unloader = transforms.ToPILImage()
plt.ion()
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)
def gram_matrix(input):
a, b, c, d = input.size() # a=batch size(=1)
features = input.view(a * b, c * d) # resise F_XL into \hat F_XL
G = torch.mm(features, features.t()) # compute the gram product
# normalization factor
return G.div(a * b * c * d)
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 = gram_matrix(target_feature).detach()
def forward(self, input):
G = gram_matrix(input)
self.loss = F.mse_loss(G, self.target)
return input
class Normalization(nn.Module):
def __init__(self, mean, std):
super(Normalization, self).__init__()
self.mean = mean.view(-1, 1, 1)
self.std = std.view(-1, 1, 1)
def forward(self, img):
return (img - self.mean) / self.std
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)
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):
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
def get_input_optimizer(input_img):
optimizer = optim.LBFGS([input_img])
return optimizer
def run_style_transfer(cnn, normalization_mean, normalization_std,
content_img, style_img, input_img, num_steps=300,
style_weight=1000000, content_weight=1):
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 = get_input_optimizer(input_img)
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
def save_output_image(image, output_path):
try:
image.save(output_path)
print(f"Output image saved successfully at {output_path}")
except Exception as e:
print(f"An error occurred while saving the output image: {str(e)}")
def convert_to_pil_image(tensor):
image = tensor.squeeze(0).cpu().clone().detach().numpy().transpose(1, 2, 0)
image = image.clip(0, 1)
image = (image * 255).astype('uint8')
return Image.fromarray(image)
num_steps = 500
style_weight = 1000000000
content_weight = 1
input_img = content_img.clone()
output = run_style_transfer(cnn, cnn_normalization_mean, cnn_normalization_std,
content_img, style_img, input_img, num_steps=num_steps,
style_weight=style_weight, content_weight=content_weight)
output_image = convert_to_pil_image(output)
output_path = "output_image.jpg"
save_output_image(output_image, output_path)
# Display content, style, and output images in a single row
fig, axes = plt.subplots(1, 3, figsize=(15, 5))
axes[0].imshow(content_img.squeeze(0).permute(1, 2, 0).cpu().numpy())
axes[0].set_title('Content Image')
axes[0].axis('off')
axes[1].imshow(style_img.squeeze(0).permute(1, 2, 0).cpu().numpy())
axes[1].set_title('Style Image')
axes[1].axis('off')
axes[2].imshow(output_image)
axes[2].set_title('Output Image')
axes[2].axis('off')
plt.tight_layout()
plt.show()