File size: 5,118 Bytes
317b678
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# From https://github.com/carolineec/informative-drawings
# MIT License
'''
MIT License

Copyright (c) 2022 Caroline Chan

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
'''

import os
import cv2
import torch
import numpy as np

import torch.nn as nn
from einops import rearrange
from .utils import load_file_from_url


norm_layer = nn.InstanceNorm2d


class ResidualBlock(nn.Module):
    def __init__(self, in_features):
        super(ResidualBlock, self).__init__()

        conv_block = [  nn.ReflectionPad2d(1),
                        nn.Conv2d(in_features, in_features, 3),
                        norm_layer(in_features),
                        nn.ReLU(inplace=True),
                        nn.ReflectionPad2d(1),
                        nn.Conv2d(in_features, in_features, 3),
                        norm_layer(in_features)
                        ]

        self.conv_block = nn.Sequential(*conv_block)

    def forward(self, x):
        return x + self.conv_block(x)


class Generator(nn.Module):
    def __init__(self, input_nc, output_nc, n_residual_blocks=9, sigmoid=True):
        super(Generator, self).__init__()

        # Initial convolution block
        model0 = [   nn.ReflectionPad2d(3),
                    nn.Conv2d(input_nc, 64, 7),
                    norm_layer(64),
                    nn.ReLU(inplace=True) ]
        self.model0 = nn.Sequential(*model0)

        # Downsampling
        model1 = []
        in_features = 64
        out_features = in_features*2
        for _ in range(2):
            model1 += [  nn.Conv2d(in_features, out_features, 3, stride=2, padding=1),
                        norm_layer(out_features),
                        nn.ReLU(inplace=True) ]
            in_features = out_features
            out_features = in_features*2
        self.model1 = nn.Sequential(*model1)

        model2 = []
        # Residual blocks
        for _ in range(n_residual_blocks):
            model2 += [ResidualBlock(in_features)]
        self.model2 = nn.Sequential(*model2)

        # Upsampling
        model3 = []
        out_features = in_features//2
        for _ in range(2):
            model3 += [  nn.ConvTranspose2d(in_features, out_features, 3, stride=2, padding=1, output_padding=1),
                        norm_layer(out_features),
                        nn.ReLU(inplace=True) ]
            in_features = out_features
            out_features = in_features//2
        self.model3 = nn.Sequential(*model3)

        # Output layer
        model4 = [  nn.ReflectionPad2d(3),
                        nn.Conv2d(64, output_nc, 7)]
        if sigmoid:
            model4 += [nn.Sigmoid()]

        self.model4 = nn.Sequential(*model4)

    def forward(self, x, cond=None):
        out = self.model0(x)
        out = self.model1(out)
        out = self.model2(out)
        out = self.model3(out)
        out = self.model4(out)

        return out


class LineartDetector:
    def __init__(self, model_path="hf_download"):
        self.model = self.load_model('sk_model.pth', model_path)
        self.model_coarse = self.load_model('sk_model2.pth', model_path)

    def load_model(self, name, model_path="hf_download"):
        remote_model_path = "https://huggingface.co/lllyasviel/Annotators/resolve/main/" + name
        modelpath = os.path.join(model_path, name)
        if not os.path.exists(modelpath):
            load_file_from_url(remote_model_path, model_dir=model_path)
        model = Generator(3, 1, 3)
        model.load_state_dict(torch.load(modelpath, map_location=torch.device('cpu')))
        model.eval()
        model = model.cuda()
        return model

    def __call__(self, input_image, coarse=False):
        model = self.model_coarse if coarse else self.model
        assert input_image.ndim == 3
        image = input_image
        with torch.no_grad():
            image = torch.from_numpy(image).float().cuda()
            image = image / 255.0
            image = rearrange(image, 'h w c -> 1 c h w')
            line = model(image)[0][0]

            line = line.cpu().numpy()
            line = (line * 255.0).clip(0, 255).astype(np.uint8)

            return line