-
Notifications
You must be signed in to change notification settings - Fork 1
/
loaders.py
244 lines (197 loc) · 11.1 KB
/
loaders.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
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
import json
import os
import pickle
from collections import namedtuple
import torch
import torch.utils.data as data
from PIL import Image
from torchvision.transforms import ToTensor
class SampleLoader(data.Dataset):
def __init__(self, samples_dir='./data/YBB/val_samples_small.pkl'):
with open(samples_dir, 'rb') as f:
self.samples = pickle.load(f)
self.to_tensor = ToTensor()
def __len__(self):
return len(self.samples)
def __getitem__(self, item):
sample = self.samples[item]
app_vec = sample['app_vec']
mask_npy = sample['mask']
keypoints_npy = sample['keypoints']
app_vec_t = torch.from_numpy(app_vec).unsqueeze(0).float()
mask_t = torch.from_numpy(mask_npy).clamp_(0, 1).unsqueeze(0).float()
keypoints_t = torch.from_numpy(keypoints_npy).clamp_(0, 1).float()
assert mask_t.max() <= 1.0, mask_t.max()
assert keypoints_t.max() <= 1.0, keypoints_t.max()
data = {'app_vec': app_vec_t, 'mask': mask_t, 'keypoints': keypoints_t}
return data
class Cityscapes(data.Dataset):
"""`Cityscapes <http://www.cityscapes-dataset.com/>`_ Dataset.
Args:
root (string): Root directory of dataset where directory ``leftImg8bit``
and ``gtFine`` or ``gtCoarse`` are located.
split (string, optional): The image split to use, ``train``, ``test`` or ``val`` if mode="gtFine"
otherwise ``train``, ``train_extra`` or ``val``
mode (string, optional): The quality mode to use, ``gtFine`` or ``gtCoarse``
target_type (string or list, optional): Type of target to use, ``instance``, ``semantic``, ``polygon``
or ``color``. Can also be a list to output a tuple with all specified target types.
transform (callable, optional): A function/random_transform that takes in a PIL image
and returns a transformed version. E.g, ``random_transform.RandomCrop``
target_transform (callable, optional): A function/random_transform that takes in the
target and random_transform it.
Examples:
Get semantic segmentation target
.. code-block:: python
dataset = Cityscapes('./data/cityscapes', split='train', mode='fine',
target_type='semantic')
img, smnt = dataset[0]
Get multiple targets
.. code-block:: python
dataset = Cityscapes('./data/cityscapes', split='train', mode='fine',
target_type=['instance', 'color', 'polygon'])
img, (inst, col, poly) = dataset[0]
Validate on the "coarse" set
.. code-block:: python
dataset = Cityscapes('./data/cityscapes', split='val', mode='coarse',
target_type='semantic')
img, smnt = dataset[0]
"""
# Based on https://github.com/mcordts/cityscapesScripts
CityscapesClass = namedtuple('CityscapesClass', ['dataset_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, split='train', mode='fine', target_type='instance',
transform=None, target_transform=None):
self.root = os.path.expanduser(root)
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.transform = transform
self.target_transform = target_transform
self.target_type = target_type
self.split = split
self.images = []
self.targets = []
self.file_paths = []
if mode not in ['fine', 'coarse']:
raise ValueError('Invalid mode! Please use mode="fine" or mode="coarse"')
if mode == 'fine' and split not in ['train', 'test', 'val']:
raise ValueError('Invalid split for mode "fine"! Please use split="train", split="test"'
' or split="val"')
elif mode == 'coarse' and split not in ['train', 'train_extra', 'val']:
raise ValueError('Invalid split for mode "coarse"! Please use split="train", split="train_extra"'
' or split="val"')
if not isinstance(target_type, list):
self.target_type = [target_type]
if not all(t in ['instance', 'semantic', 'polygon', 'color'] for t in self.target_type):
raise ValueError('Invalid value for "target_type"! Valid values are: "instance", "semantic", "polygon"'
' or "color"')
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):
img_dir = os.path.join(self.images_dir, city)
if not os.path.isdir(img_dir):
continue
target_dir = os.path.join(self.targets_dir, city)
for file_name in os.listdir(img_dir):
ext = file_name.split('.')[-1]
if ext not in ['jpg', 'png']:
continue
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)
self.file_paths.append(os.path.join(img_dir, file_name))
def __getitem__(self, index):
"""
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.
"""
path = self.file_paths[index]
image = Image.open(self.images[index]).convert('RGB')
image.crop()
targets = []
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.transform:
image = self.transform(image)
if self.target_transform:
target = self.target_transform(target)
return path, image, target
def __len__(self):
return len(self.images)
def __repr__(self):
fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
fmt_str += ' Number of datapoints: {}\n'.format(self.__len__())
fmt_str += ' Split: {}\n'.format(self.split)
fmt_str += ' Mode: {}\n'.format(self.mode)
fmt_str += ' Type: {}\n'.format(self.target_type)
fmt_str += ' Root Location: {}\n'.format(self.root)
tmp = ' Transforms (if any): '
fmt_str += '{0}{1}\n'.format(tmp, self.transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
tmp = ' Target Transforms (if any): '
fmt_str += '{0}{1}'.format(tmp, self.target_transform.__repr__().replace('\n', '\n' + ' ' * len(tmp)))
return fmt_str
def _load_json(self, path):
with open(path, 'r') as file:
data = json.load(file)
return data
def _get_target_suffix(self, mode, target_type):
if target_type == 'instance':
return '{}_instanceIds.png'.format(mode)
elif target_type == 'semantic':
return '{}_labelIds.png'.format(mode)
elif target_type == 'color':
return '{}_color.png'.format(mode)
else:
return '{}_polygons.json'.format(mode)
def get_loader(cs_dir, target_type):
return Cityscapes(cs_dir, target_type=target_type), SampleLoader()