File size: 7,669 Bytes
f7f604d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
from email.mime import base
import numpy as np
from PIL import Image
import os
import sys
import torch
import torch.nn.functional as F
from PIL import Image, ImageOps, ImageFilter, ImageEnhance
from typing import Optional

filepath = os.path.split(__file__)[0]
repopath = os.path.split(filepath)[0]
sys.path.append(repopath)

from utils.misc import *
        
class static_resize:
    # Resize for training
    # size: h x w
    def __init__(self, size=[384, 384], base_size=None):
        self.size = size[::-1]
        self.base_size = base_size[::-1] if base_size is not None else None
            
    def __call__(self, sample):
        sample['image'] = sample['image'].resize(self.size, Image.BILINEAR)
        if 'gt' in sample.keys():
            sample['gt'] = sample['gt'].resize(self.size, Image.NEAREST)
            
        if self.base_size is not None:
            sample['image_resized'] = sample['image'].resize(self.size, Image.BILINEAR)
            if 'gt' in sample.keys():
                sample['gt_resized'] = sample['gt'].resize(self.size, Image.NEAREST)
                
        return sample

class dynamic_resize:
    # base_size: h x w
    def __init__(self, L=1280, base_size=[384, 384]): 
        self.L = L
        self.base_size = base_size[::-1]
                    
    def __call__(self, sample):
        size = list(sample['image'].size)
        if (size[0] >= size[1]) and size[1] > self.L: 
            size[0] = size[0] / (size[1] / self.L)
            size[1] = self.L
        elif (size[1] > size[0]) and size[0] > self.L:
            size[1] = size[1] / (size[0] / self.L)
            size[0] = self.L
        size = (int(round(size[0] / 32)) * 32, int(round(size[1] / 32)) * 32)
    
        if 'image' in sample.keys():
            sample['image_resized'] = sample['image'].resize(self.base_size, Image.BILINEAR)
            sample['image'] = sample['image'].resize(size, Image.BILINEAR)
            
        if 'gt' in sample.keys():
            sample['gt_resized'] = sample['gt'].resize(self.base_size, Image.NEAREST)
            sample['gt'] = sample['gt'].resize(size, Image.NEAREST)
        
        return sample
        
class random_scale_crop:
    def __init__(self, range=[0.75, 1.25]):
        self.range = range

    def __call__(self, sample):
        scale = np.random.random() * (self.range[1] - self.range[0]) + self.range[0]
        if np.random.random() < 0.5:
            for key in sample.keys():
                if key in ['image', 'gt']:
                    base_size = sample[key].size

                    scale_size = tuple((np.array(base_size) * scale).round().astype(int))
                    sample[key] = sample[key].resize(scale_size)

                    lf = (sample[key].size[0] - base_size[0]) // 2
                    up = (sample[key].size[1] - base_size[1]) // 2
                    rg = (sample[key].size[0] + base_size[0]) // 2
                    lw = (sample[key].size[1] + base_size[1]) // 2

                    border = -min(0, min(lf, up))
                    sample[key] = ImageOps.expand(sample[key], border=border)
                    sample[key] = sample[key].crop((lf + border, up + border, rg + border, lw + border))
        return sample

class random_flip:
    def __init__(self, lr=True, ud=True):
        self.lr = lr
        self.ud = ud

    def __call__(self, sample):
        lr = np.random.random() < 0.5 and self.lr is True
        ud = np.random.random() < 0.5 and self.ud is True

        for key in sample.keys():
            if key in ['image', 'gt']:
                sample[key] = np.array(sample[key])
                if lr:
                    sample[key] = np.fliplr(sample[key])
                if ud:
                    sample[key] = np.flipud(sample[key])
                sample[key] = Image.fromarray(sample[key])

        return sample

class random_rotate:
    def __init__(self, range=[0, 360], interval=1):
        self.range = range
        self.interval = interval

    def __call__(self, sample):
        rot = (np.random.randint(*self.range) // self.interval) * self.interval
        rot = rot + 360 if rot < 0 else rot

        if np.random.random() < 0.5:
            for key in sample.keys():
                if key in ['image', 'gt']:
                    base_size = sample[key].size
                    sample[key] = sample[key].rotate(rot, expand=True, fillcolor=255 if key == 'depth' else None)

                    sample[key] = sample[key].crop(((sample[key].size[0] - base_size[0]) // 2,
                                                    (sample[key].size[1] - base_size[1]) // 2,
                                                    (sample[key].size[0] + base_size[0]) // 2,
                                                    (sample[key].size[1] + base_size[1]) // 2))

        return sample

class random_image_enhance:
    def __init__(self, methods=['contrast', 'brightness', 'sharpness']):
        self.enhance_method = []
        if 'contrast' in methods:
            self.enhance_method.append(ImageEnhance.Contrast)
        if 'brightness' in methods:
            self.enhance_method.append(ImageEnhance.Brightness)
        if 'sharpness' in methods:
            self.enhance_method.append(ImageEnhance.Sharpness)

    def __call__(self, sample):
        if 'image' in sample.keys():
            np.random.shuffle(self.enhance_method)

            for method in self.enhance_method:
                if np.random.random() > 0.5:
                    enhancer = method(sample['image'])
                    factor = float(1 + np.random.random() / 10)
                    sample['image'] = enhancer.enhance(factor)

        return sample

class tonumpy:
    def __init__(self):
        pass

    def __call__(self, sample):
        for key in sample.keys():
            if key in ['image', 'image_resized', 'gt', 'gt_resized']:
                sample[key] = np.array(sample[key], dtype=np.float32)

        return sample

class normalize:
    def __init__(self, mean: Optional[list]=None, std: Optional[list]=None, div=255):
        self.mean = mean if mean is not None else 0.0
        self.std = std if std is not None else 1.0
        self.div = div
        
    def __call__(self, sample):
        if 'image' in sample.keys():
            sample['image'] /= self.div
            sample['image'] -= self.mean
            sample['image'] /= self.std
            
        if 'image_resized' in sample.keys():
            sample['image_resized'] /= self.div
            sample['image_resized'] -= self.mean
            sample['image_resized'] /= self.std

        if 'gt' in sample.keys():
            sample['gt'] /= self.div
            
        if 'gt_resized' in sample.keys():
            sample['gt_resized'] /= self.div

        return sample
class totensor:
    def __init__(self):
        pass

    def __call__(self, sample):
        if 'image' in sample.keys():
            sample['image'] = sample['image'].transpose((2, 0, 1))
            sample['image'] = torch.from_numpy(sample['image']).float()
        
        if 'image_resized' in sample.keys():
            sample['image_resized'] = sample['image_resized'].transpose((2, 0, 1))
            sample['image_resized'] = torch.from_numpy(sample['image_resized']).float()
            
        if 'gt' in sample.keys():
            sample['gt'] = torch.from_numpy(sample['gt'])
            sample['gt'] = sample['gt'].unsqueeze(dim=0)
            
        if 'gt_resized' in sample.keys():
            sample['gt_resized'] = torch.from_numpy(sample['gt_resized'])
            sample['gt_resized'] = sample['gt_resized'].unsqueeze(dim=0)

        return sample