这几天把图片迁移的代码运行出来，感觉很开心！😘
之前在github上找了很多关于图片风格迁移的代码，但都没有运行出来，有可能是我的电脑不支持GPU加速。后来买了本书《python深度学习基于pytorch》，书上有相关代码的介绍。市面上关于pytorch深度学习的书籍相对较少，这本是我在豆瓣上看到利用pytorch进行深度学习评分较高的一本，兼顾了CPU和GPU。先上图让大家看看效果：
原代码链接
上面一张图的图片内容损失有点大，几乎看不出原来图形的轮廓；下面一张还行，就是天空那部分有点问题，可能多运行几次效果会好点。运行代码，差不多要半个小时，这是第一次我感觉到CPU的局限。下面直接上代码：
代码：
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
# 有GPU就利用GPU没有就利用CPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# 指定输出图像大小
imsize = 512 if torch.cuda.is_available() else 450 # 标准：450 560 / 200 300
imsize_w = 600
# 对图像进行预处理
loader = transforms.Compose([
transforms.Resize((imsize, imsize_w)),
transforms.ToTensor()
])
def image_loader(image_name):
image = Image.open(image_name)
# 增加一个维度，其值为1
# 这是为了满足神经网络对输入图像的形状要求
image = loader(image).unsqueeze(0)
return image.to(device, torch.float)
style_img = image_loader('pic_1.jpg')
content_img = image_loader('pic_2.jpg')
print('style size', style_img.size())
print('content size', content_img.size())
assert style_img.size() == content_img.size()
输出图片尺寸：
(PS:上面pic_1和pic_2根据自己喜好选择相应图片，pic_1为风格图片，pic_2为要转换的图片)
style size torch.Size([1, 3, 450, 600])
content size torch.Size([1, 3, 450, 600])
代码：
unloader = transforms.ToPILImage()
plt.ion()
def imshow(tensor, title=None):
image = tensor.cpu().clone() # 为避免因image修改影响tensor的值
image = image.squeeze(0) # 去掉批量这个维度
image = unloader(image)
plt.imshow(image)
if title is not None:
plt.title(title)
plt.pause(0.001) # 暂停一下让图片能更新
plt.figure()
imshow(style_img, title='Style Image')
plt.figure()
imshow(content_img, title='Content Image')
输出图片：
代码：
class ContentLoss(nn.Module):
def __init__(self, target):
super(ContentLoss, self).__init__()
# 必须要用detach来分离出target,这时候target不再是一个Variable
# 这是为了动态计算梯度，否则forward会出错，不能向前传播
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()) # 计算内积
# 对拉格姆矩阵标准化
# 通过对其处理以特征图像总数
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
输出：
Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace=True)
(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU(inplace=True)
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU(inplace=True)
(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU(inplace=True)
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU(inplace=True)
(16): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(17): ReLU(inplace=True)
(18): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(19): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU(inplace=True)
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU(inplace=True)
(23): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(24): ReLU(inplace=True)
(25): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(26): ReLU(inplace=True)
(27): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU(inplace=True)
(30): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(31): ReLU(inplace=True)
(32): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(33): ReLU(inplace=True)
(34): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(35): ReLU(inplace=True)
(36): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
代码：
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 = mean.clone().detach().view(-1, 1, 1)
self.std = std.clone().detach().view(-1, 1, 1)
def forward(self, img):
return (img - self.mean) / self.std
# 为计算内容损失和风格损失，指定使用的内卷层
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)
# 标准化模型
normalization = Normalization(normalization_mean, normalization_std).to(device)
# 初始化损失值
content_losses = []
style_losses = []
# 使用sequential方法构建模型
model = nn.Sequential(normalization)
i = 0 # 每次迭代增加1
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.BachNorm2d):
name = 'bn_{}'.format(i)
else:
raise RuntimeError('Unrecognized layer:{}'.format(layer.__class__.__name__))
model.add_module(name, layer)
if name in content_layers:
# 累加内容损失
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:
# 累加风格损失
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)
# 我们需要对在内容损失和风格损失之后的层进行修建
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
# 复制content_img
input_img = content_img.clone()
plt.figure()
# 我这里去掉了刻度和坐标轴
plt.axis('off')
plt.xticks([])
plt.yticks([])
imshow(input_img, title='Input Image')
输出：
代码：
def get_input_optimizer(input_img):
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=600,
style_weight=1000000, content_weight=1):
"""返回风格"""
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():
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)
input_img.data.clamp_(0, 1)
return input_img
output = run_style_transfer(cnn, cnn_normalization_mean, cnn_normalization_std,
content_img, style_img, input_img)
plt.figure()
plt.xticks([])
plt.yticks([])
plt.axis('off')
imshow(output, title='Output Image')
plt.ioff()
plt.show()
输出结果：
Building the style transfer model..
Optimizing..
run [50]:
Style Loss: 71.486160 Content Loss: 13.809214
run [100]:
Style Loss: 40.491692 Content Loss: 14.122237
run [150]:
Style Loss: 25.580254 Content Loss: 13.938315
run [200]:
Style Loss: 13.806768 Content Loss: 14.290324
run [250]:
Style Loss: 6.078248 Content Loss: 14.245186
run [300]:
Style Loss: 3.660152 Content Loss: 13.365716
run [350]:
Style Loss: 3.001604 Content Loss: 12.663176
run [400]:
Style Loss: 2.334168 Content Loss: 12.076923
run [450]:
Style Loss: 2.023839 Content Loss: 11.745106
run [500]:
Style Loss: 1.812191 Content Loss: 11.482430
run [550]:
Style Loss: 1.663573 Content Loss: 11.269305
run [600]:
Style Loss: 1.579811 Content Loss: 11.157408
完结撒花！
本人小白一枚，写博客一方面是加深自己的印象，另一方面可以和大家交流学习，若有写的不对的地方，还请大家批评指正，以免误导他人学习！😁
1564
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
