-
Notifications
You must be signed in to change notification settings - Fork 8
/
cityscapes_dataloader.py
175 lines (146 loc) · 8.47 KB
/
cityscapes_dataloader.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
import os
import os.path as osp
import numpy as np
import random
import matplotlib.pyplot as plt
import collections
from collections import namedtuple
import torch
import torchvision
from torch.utils import data
from PIL import Image
class cityscapesDataSet(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, 255, 'vehicle', 7, False, True, (0, 0, 142)),
]
train_id_to_color = [c.color for c in classes if (c.train_id != -1 and c.train_id != 255)]
train_id_to_color.append([0, 0, 0])
train_id_to_color = np.array(train_id_to_color)
id_to_train_id = np.array([c.train_id for c in classes])
def __init__(self, root, list_path, max_iters=None, crop_size=(321, 321), mean=(128, 128, 128), scale=True, mirror=True, ignore_label=255, set='val',split='val', mode='fine', target_type='semantic', transform=None):
self.root = root
self.list_path = list_path
self.crop_size = crop_size
self.scale = scale
self.ignore_label = ignore_label
self.mean = mean
self.is_mirror = mirror
# self.mean_bgr = np.array([104.00698793, 116.66876762, 122.67891434])
self.img_ids = [i_id.strip() for i_id in open(list_path)]
if not max_iters==None:
self.img_ids = self.img_ids * int(np.ceil(float(max_iters) / len(self.img_ids)))
self.files = []
self.set = set
# for split in ["train", "trainval", "val"]:
for name in self.img_ids:
img_file = osp.join(self.root, "leftImg8bit/%s/%s" % (self.set, name))
self.files.append({
"img": img_file,
"name": name
})
############### for real data ################
self.root_adapt = os.path.expanduser(root)
self.mode = 'gtFine'
self.target_type = target_type
self.images_dir = os.path.join(self.root_adapt, 'leftImg8bit', split)
self.targets_dir = os.path.join(self.root_adapt, self.mode, split)
self.transform = transform
self.split = split
self.images = []
self.targets = []
self.name_real = []
if split not in ['train', 'test', 'val']:
raise ValueError('Invalid split for mode! Please use split="train", split="test"'
' or split="val"')
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)
target_dir = os.path.join(self.targets_dir, city)
for file_name in os.listdir(img_dir):
self.images.append(os.path.join(img_dir, file_name))
target_name = '{}_{}'.format(file_name.split('_leftImg8bit')[0],
self._get_target_suffix(self.mode, self.target_type))
self.targets.append(os.path.join(target_dir, target_name))
self.name_real.append(file_name)
@classmethod
def encode_target(cls, target):
return cls.id_to_train_id[np.array(target)]
@classmethod
def decode_target(cls, target):
target[target == 255] = 19
#target = target.astype('uint8') + 1
return cls.train_id_to_color[target]
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)
elif target_type == 'polygon':
return '{}_polygons.json'.format(mode)
elif target_type == 'depth':
return '{}_disparity.png'.format(mode)
def __len__(self):
return len(self.images)
def __getitem__(self, index):
# print("i am in getitem")
########## for adaptive channel #########
datafiles = self.files[index]
image = Image.open(datafiles["img"]).convert('RGB')
name = datafiles["name"]
# resize
image = image.resize(self.crop_size, Image.BICUBIC)
image = np.asarray(image, np.float32)
size = image.shape
image = image[:, :, ::-1] # change to BGR
image -= self.mean
image = image.transpose((2, 0, 1))
####### for real channel #########
image_real = Image.open(self.images[index]).convert('RGB')
# print(image_real)
target_real = Image.open(self.targets[index])
print("name from adapt", name)
print("name from real", self.images[index])
if self.transform:
image_real, target_real = self.transform(image_real, target_real)
target_real = self.encode_target(target_real)
return image.copy(), np.array(size), name , image_real , target_real