-
Notifications
You must be signed in to change notification settings - Fork 3
/
cityscapes.py
138 lines (119 loc) · 6.73 KB
/
cityscapes.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
import json
import os
from collections import namedtuple
from typing import Any, Callable, Dict, List, Optional, Union, Tuple
import torch.utils.data as data
from PIL import Image
class Cityscapes(data.Dataset):
CityscapesClass = namedtuple('CityscapesClass', ['name', 'id', 'train_id', 'category', 'category_id',
'has_instances', 'ignore_in_eval', 'color'])
classes = [
CityscapesClass('unlabeled', 0, 255, 'void', 0, False, True, (0, 0, 0)),
CityscapesClass('ego vehicle', 1, 255, 'void', 0, False, True, (0, 0, 0)),
CityscapesClass('rectification border', 2, 255, 'void', 0, False, True, (0, 0, 0)),
CityscapesClass('out of roi', 3, 255, 'void', 0, False, True, (0, 0, 0)),
CityscapesClass('static', 4, 255, 'void', 0, False, True, (0, 0, 0)),
CityscapesClass('dynamic', 5, 255, 'void', 0, False, True, (111, 74, 0)),
CityscapesClass('ground', 6, 255, 'void', 0, False, True, (81, 0, 81)),
CityscapesClass('road', 7, 0, 'flat', 1, False, False, (128, 64, 128)),
CityscapesClass('sidewalk', 8, 1, 'flat', 1, False, False, (244, 35, 232)),
CityscapesClass('parking', 9, 255, 'flat', 1, False, True, (250, 170, 160)),
CityscapesClass('rail track', 10, 255, 'flat', 1, False, True, (230, 150, 140)),
CityscapesClass('building', 11, 2, 'construction', 2, False, False, (70, 70, 70)),
CityscapesClass('wall', 12, 3, 'construction', 2, False, False, (102, 102, 156)),
CityscapesClass('fence', 13, 4, 'construction', 2, False, False, (190, 153, 153)),
CityscapesClass('guard rail', 14, 255, 'construction', 2, False, True, (180, 165, 180)),
CityscapesClass('bridge', 15, 255, 'construction', 2, False, True, (150, 100, 100)),
CityscapesClass('tunnel', 16, 255, 'construction', 2, False, True, (150, 120, 90)),
CityscapesClass('pole', 17, 5, 'object', 3, False, False, (153, 153, 153)),
CityscapesClass('polegroup', 18, 255, 'object', 3, False, True, (153, 153, 153)),
CityscapesClass('traffic light', 19, 6, 'object', 3, False, False, (250, 170, 30)),
CityscapesClass('traffic sign', 20, 7, 'object', 3, False, False, (220, 220, 0)),
CityscapesClass('vegetation', 21, 8, 'nature', 4, False, False, (107, 142, 35)),
CityscapesClass('terrain', 22, 9, 'nature', 4, False, False, (152, 251, 152)),
CityscapesClass('sky', 23, 10, 'sky', 5, False, False, (70, 130, 180)),
CityscapesClass('person', 24, 11, 'human', 6, True, False, (220, 20, 60)),
CityscapesClass('rider', 25, 12, 'human', 6, True, False, (255, 0, 0)),
CityscapesClass('car', 26, 13, 'vehicle', 7, True, False, (0, 0, 142)),
CityscapesClass('truck', 27, 14, 'vehicle', 7, True, False, (0, 0, 70)),
CityscapesClass('bus', 28, 15, 'vehicle', 7, True, False, (0, 60, 100)),
CityscapesClass('caravan', 29, 255, 'vehicle', 7, True, True, (0, 0, 90)),
CityscapesClass('trailer', 30, 255, 'vehicle', 7, True, True, (0, 0, 110)),
CityscapesClass('train', 31, 16, 'vehicle', 7, True, False, (0, 80, 100)),
CityscapesClass('motorcycle', 32, 17, 'vehicle', 7, True, False, (0, 0, 230)),
CityscapesClass('bicycle', 33, 18, 'vehicle', 7, True, False, (119, 11, 32)),
CityscapesClass('license plate', -1, -1, 'vehicle', 7, False, True, (0, 0, 142)),
]
def __init__(
self,
root: str,
split: str = "train",
mode: str = "fine",
target_type: Union[List[str], str] = "semantic",
transforms: Optional[Callable] = None,
) -> None:
self.root=root
self.transforms=transforms
self.mode = 'gtFine' if mode == 'fine' else 'gtCoarse'
self.images_dir = os.path.join(self.root, 'leftImg8bit', split)
self.targets_dir = os.path.join(self.root, self.mode, split)
self.target_type = target_type
self.split = split
self.images = []
self.targets = []
if not isinstance(target_type, list):
self.target_type = [target_type]
if not os.path.isdir(self.images_dir) or not os.path.isdir(self.targets_dir):
raise RuntimeError('Dataset not found or incomplete. Please make sure all required folders for the'
' specified "split" and "mode" are inside the "root" directory')
for city in os.listdir(self.images_dir):
if city[0]==".":
continue
img_dir = os.path.join(self.images_dir, city)
target_dir = os.path.join(self.targets_dir, city)
for file_name in os.listdir(img_dir):
target_types = []
for t in self.target_type:
target_name = '{}_{}'.format(file_name.split('_leftImg8bit')[0],
self._get_target_suffix(self.mode, t))
target_types.append(os.path.join(target_dir, target_name))
self.images.append(os.path.join(img_dir, file_name))
self.targets.append(target_types)
def __getitem__(self, index: int) -> Tuple[Any, Any]:
"""
Args:
index (int): Index
Returns:
tuple: (image, target) where target is a tuple of all target types if target_type is a list with more
than one item. Otherwise target is a json object if target_type="polygon", else the image segmentation.
"""
image = Image.open(self.images[index]).convert('RGB')
targets: Any = []
for i, t in enumerate(self.target_type):
if t == 'polygon':
target = self._load_json(self.targets[index][i])
else:
target = Image.open(self.targets[index][i])
targets.append(target)
target = tuple(targets) if len(targets) > 1 else targets[0]
if self.transforms is not None:
image, target = self.transforms(image, target)
return image, target
def __len__(self) -> int:
return len(self.images)
def extra_repr(self) -> str:
lines = ["Split: {split}", "Mode: {mode}", "Type: {target_type}"]
return '\n'.join(lines).format(**self.__dict__)
def _load_json(self, path: str) -> Dict[str, Any]:
with open(path, 'r') as file:
data = json.load(file)
return data
def _get_target_suffix(self, mode: str, target_type: str) -> str:
if target_type == 'instance':
return '{}_instanceIds.png'.format(mode)
elif target_type == 'semantic':
return '{}_labelTrainIds.png'.format(mode)
elif target_type == 'color':
return '{}_color.png'.format(mode)
else:
return '{}_polygons.json'.format(mode)