-
Notifications
You must be signed in to change notification settings - Fork 0
/
model.py
188 lines (159 loc) · 6.55 KB
/
model.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
import copy
import io
import os
from io import BytesIO
import torch
from PIL import Image
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
import matplotlib.pyplot as plt
import torchvision.models as models
import torchvision.transforms as transforms
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
imsize = 512
loader = transforms.Compose([transforms.CenterCrop(imsize), transforms.ToTensor()])
unloader = transforms.ToPILImage()
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 image_loader(image_name):
image = Image.open(image_name)
if image.size[0] > 2 * imsize and image.size[1] > 2 * imsize:
times = min(image.size[0], image.size[1]) / imsize
new_size = (int(image.size[0] / times), int(image.size[1] / times))
image = image.resize(new_size)
image = loader(image).unsqueeze(0)
return image.to(device, torch.float)
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 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.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
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 = '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:
# 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)
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.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):
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)
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()))
return style_score + content_score
optimizer.step(closure)
input_img.data.clamp_(0, 1)
return input_img
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 generate(style_img_path, content_image, num_iteration=50):
content_image = BytesIO(content_image)
style_image = image_loader(os.path.join("frontend", "style", style_img_path))
content_image = image_loader(content_image)
input_img = content_image.clone()
output_image = run_style_transfer(cnn, cnn_normalization_mean, cnn_normalization_std,
content_image, style_image, input_img, num_steps=num_iteration)
image = output_image.cpu().clone()
image = image.squeeze(0)
image = unloader(image)
img_byte_arr = io.BytesIO()
image.save(img_byte_arr, format='PNG')
img_byte_arr = img_byte_arr.getvalue()
return img_byte_arr
if __name__ == '__main__':
with open("test.png", 'rb') as f:
content_image = f.read()
result = generate('44296041_16.jpg', content_image, num_iteration=50)
with open("result.png", 'wb') as f:
f.write(result)