版权声明:本文为博主原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明。
实现由 Leon A. Gatys,Alexander S. Ecker和Matthias Bethge提出的Neural-Style 算法。Neural-Style 或者叫 Neural-Transfer,可以让你使用一种新的风格将指定的图片进行重构。
这个算法使用三张图片,一张输入图片,一张内容图片和一张风格图片,并将输入的图片变得与内容图片相似,且拥有风格图片的优美风格。
定义两个间距,一个用于内容D_C
,另一个用于风格D_S
。D_C
测量两张图片内容的不同,而D_S
用来测量两张图片风格的不同。然后,我们输入第三张图片,并改变这张图片,使其与内容图片的内容间距和风格图片的风格间距最小化。
关于矩阵特征分解:https://blog.csdn.net/wsp_1138886114/article/details/80967843
权重下载:默认运行时下载,或者百度云。提取码: gun8
from __future__ import print_function
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
def load_img(content_path,style_path):
loader = transforms.Compose([
transforms.Resize(imsize), # scale imported image
transforms.ToTensor()]) # transform it into a torch tensor
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_path)
content_img = image_loader(content_path)
assert style_img.size() == content_img.size()
return style_img,content_img
def imshow(tensor, title=None):
image = tensor.cpu().clone() # we clone the tensor to not do changes on it
image = image.squeeze(0) # remove the fake batch dimension
image = transforms.ToPILImage()(image)
plt.imshow(image)
if title is not None:
plt.title(title)
plt.pause(0.001) # pause a bit so that plots are updated
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() # 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
return G.div(a * b * c * d) # 我们通过除以每个特征映射中的元素数来“标准化”gram矩阵的值.
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 = 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
# 期望的深度层来计算样式/内容损失:
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)
# 规范化模块
normalization = Normalization(normalization_mean, normalization_std).to(device)
model = nn.Sequential(normalization)
content_losses = []
style_losses = []
i = 0 # increment every time we see a conv
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:
# 加入内容损失:
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:
# 加入风格损失:
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)
# 现在我们在最后的内容和风格损失之后剪掉了图层
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 run_style_transfer(cnn, normalization_mean, normalization_std,
content_img, style_img, input_img, num_steps=300,
style_weight=1000000, content_weight=1):
"""Run the style transfer."""
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)
optimizer = optim.LBFGS([input_img.requires_grad_()])
print('Optimizing..')
run = [0]
while run[0] <= num_steps:
def closure():
# 更正更新的输入图像的值
input_img.data.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)
# 最后的修正......
input_img.data.clamp_(0, 1)
return input_img
if __name__ == '__main__':
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
imsize = 512 if torch.cuda.is_available() else 128 # use small size if no gpu
content_path = "./001.png"
style_path = "./002.png"
style_img, content_img = load_img(content_path, style_path)
plt.ion()
plt.figure()
imshow(style_img, title='Style Image')
imshow(content_img, title='Content Image')
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)
input_img = content_img.clone()
# 如果您想使用白噪声而取消注释以下行:
# input_img = torch.randn(content_img.data.size(), device=device)
plt.figure()
imshow(input_img, title='Input Image')
output = run_style_transfer(cnn, cnn_normalization_mean, cnn_normalization_std,
content_img, style_img, input_img)
plt.figure()
imshow(output, title='Output Image')
plt.ioff()
plt.show()
效果如下: