风格迁移简介
平台介绍
相关软件
相关硬件
相关算法
网络架构
算法
CNN卷积神经网络
Gram矩阵,这个是风格损失的主要算法。
LBFGs算法(梯度下降方法)
代码
导入所需包及设备
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
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
加载图像
导入图像后,需要将图像大小调整为相同尺寸同时将图像的矩阵转换成tensor(这个相当于是numpy,二者的区别就在于tensor可以在GPU上运行而numpy只能在CPU上运行)。最后可以测试一下二者的size。
完成统一后还需要做向PIL image的转变,这个转变就是将输出的结果去掉通道这一项参数。
# desired size of the output image
imsize = 512 if torch.cuda.is_available() else 128 # use small size if no gpu
loader = transforms.Compose([
transforms.Resize([imsize,imsize]), # scale imported image
transforms.ToTensor()]) # transform it into a torch tensor
def image_loader(image_name):
image = Image.open(image_name)
# fake batch dimension required to fit network's input dimensions
image = loader(image).unsqueeze(0)
return image.to(device, torch.float)
style_img = image_loader("image/picasso.jpg")
content_img = image_loader("image/dancing.jpg")
print(style_img.size())
print(content_img.size())
unloader = transforms.ToPILImage() # reconvert into PIL image
plt.ion()
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 = unloader(image)
plt.imshow(image)
if title is not None:
plt.title(title)
plt.pause(0.001) # pause a bit so that plots are updated
plt.figure()
imshow(style_img, title='Style Image')
plt.figure()
imshow(content_img, title='Content Image')
损失函数=内容损失+风格损失
内容损失
我们从用于动态计算梯度的结构中“分离”目标内容:这是一个规定的值,而不是一个变量。 否则标准的 forward 方法将抛出错误。
forward()函数用于前向传递损失。
class ContentLoss(nn.Module):
def __init__(self, target,):
super(ContentLoss, self).__init__()
# we 'detach' the target content from the tree used
# to dynamically compute the gradient: this is a stated value,
# not a variable. Otherwise the forward method of the criterion
# will throw an error.
self.target = target.detach()
def forward(self, input):
self.loss = F.mse_loss(input, self.target)
return input
风格损失
这里的损失计算为均方损失即
l
o
s
s
(
x
i
,
y
i
)
=
(
x
i
−
y
i
)
2
loss(x_i,y_i)=(x_i-y_i)^2
loss(xi,yi)=(xi−yi)2
def gram_matrix(input):
a, b, c, d = input.size() # a=batch size(=1)
# b=number of feature maps
# (c,d)=dimensions of a f. map (N=c*d)
features = input.view(a * b, c * d) # resise F_XL into \hat F_XL
G = torch.mm(features, features.t()) # compute the gram product
# we 'normalize' the values of the gram matrix
# by dividing by the number of element in each feature maps.
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
导入模型,导入VGG19并初始化。定义计算风格损失的层是:conv_1,conv_2,conv_3,conv_4,conv_5以及内容损失层是conv_4。
接着就是获取模型并计算损失,先做归一化,再对每一层进行误差计算最后返回风格误差及内容误差。
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)
# create a module to normalize input image so we can easily put it in a
# nn.Sequential
class Normalization(nn.Module):
def __init__(self, mean, std):
super(Normalization, self).__init__()
# .view the mean and std to make them [C x 1 x 1] so that they can
# directly work with image Tensor of shape [B x C x H x W].
# B is batch size. C is number of channels. H is height and W is width.
self.mean = torch.tensor(mean).view(-1, 1, 1)
self.std = torch.tensor(std).view(-1, 1, 1)
def forward(self, img):
# normalize img
return (img - self.mean) / self.std
# desired depth layers to compute style/content losses :
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 module
normalization = Normalization(normalization_mean, normalization_std).to(device)
# just in order to have an iterable access to or list of content/syle
# losses
content_losses = []
style_losses = []
# assuming that cnn is a nn.Sequential, so we make a new nn.Sequential
# to put in modules that are supposed to be activated sequentially
model = nn.Sequential(normalization)
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)
# The in-place version doesn't play very nicely with the ContentLoss
# and StyleLoss we insert below. So we replace with out-of-place
# ones here.
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:
# add content loss:
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:
# add style loss:
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)
# now we trim off the layers after the last content and style losses
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
选择输入图像
input_img = content_img.clone()
# if you want to use white noise instead uncomment the below line:
# input_img = torch.randn(content_img.data.size(), device=device)
# add the original input image to the figure:
plt.figure()
imshow(input_img, title='Input Image')
梯度下降
在梯度下降中关键的一点就是保存相关的梯度信息,在这里使用到了requires_grad_()函数保证了输入信息的梯度回传。
run_style_transfer()函数就是训练,定义了训练模型CNN、归一化变量mean(记录平均值)和std(记录标准差)、输入的两张图、迭代次数、风格/内容的权重。通过前向传播将损失loss传入下一层,将损失loss乘上权重weight就是对应分数score。根据BP网络的特点,误差反向传播,更新权值。迭代次数达到设定值后返回。
def get_input_optimizer(input_img):
# this line to show that input is a parameter that requires a gradient
optimizer = optim.LBFGS([input_img.requires_grad_()])
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):
"""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 = get_input_optimizer(input_img)
print('Optimizing..')
run = [0]
while run[0] <= num_steps:
def closure():
# correct the values of updated input image
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)
# a last correction...
input_img.data.clamp_(0, 1)
return input_img
训练并输出
output = run_style_transfer(cnn, cnn_normalization_mean, cnn_normalization_std,
content_img, style_img, input_img)
plt.figure()
imshow(output, title='Output Image')
# sphinx_gallery_thumbnail_number = 4
plt.ioff()
plt.show()