-
Notifications
You must be signed in to change notification settings - Fork 180
/
datasets.py
306 lines (233 loc) · 11.1 KB
/
datasets.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
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
# camera-ready
import torch
import torch.utils.data
import numpy as np
import cv2
import os
train_dirs = ["jena/", "zurich/", "weimar/", "ulm/", "tubingen/", "stuttgart/",
"strasbourg/", "monchengladbach/", "krefeld/", "hanover/",
"hamburg/", "erfurt/", "dusseldorf/", "darmstadt/", "cologne/",
"bremen/", "bochum/", "aachen/"]
val_dirs = ["frankfurt/", "munster/", "lindau/"]
test_dirs = ["berlin", "bielefeld", "bonn", "leverkusen", "mainz", "munich"]
class DatasetTrain(torch.utils.data.Dataset):
def __init__(self, cityscapes_data_path, cityscapes_meta_path):
self.img_dir = cityscapes_data_path + "/leftImg8bit/train/"
self.label_dir = cityscapes_meta_path + "/label_imgs/"
self.img_h = 1024
self.img_w = 2048
self.new_img_h = 512
self.new_img_w = 1024
self.examples = []
for train_dir in train_dirs:
train_img_dir_path = self.img_dir + train_dir
file_names = os.listdir(train_img_dir_path)
for file_name in file_names:
img_id = file_name.split("_leftImg8bit.png")[0]
img_path = train_img_dir_path + file_name
label_img_path = self.label_dir + img_id + ".png"
example = {}
example["img_path"] = img_path
example["label_img_path"] = label_img_path
example["img_id"] = img_id
self.examples.append(example)
self.num_examples = len(self.examples)
def __getitem__(self, index):
example = self.examples[index]
img_path = example["img_path"]
img = cv2.imread(img_path, -1) # (shape: (1024, 2048, 3))
# resize img without interpolation (want the image to still match
# label_img, which we resize below):
img = cv2.resize(img, (self.new_img_w, self.new_img_h),
interpolation=cv2.INTER_NEAREST) # (shape: (512, 1024, 3))
label_img_path = example["label_img_path"]
label_img = cv2.imread(label_img_path, -1) # (shape: (1024, 2048))
# resize label_img without interpolation (want the resulting image to
# still only contain pixel values corresponding to an object class):
label_img = cv2.resize(label_img, (self.new_img_w, self.new_img_h),
interpolation=cv2.INTER_NEAREST) # (shape: (512, 1024))
# flip the img and the label with 0.5 probability:
flip = np.random.randint(low=0, high=2)
if flip == 1:
img = cv2.flip(img, 1)
label_img = cv2.flip(label_img, 1)
########################################################################
# randomly scale the img and the label:
########################################################################
scale = np.random.uniform(low=0.7, high=2.0)
new_img_h = int(scale*self.new_img_h)
new_img_w = int(scale*self.new_img_w)
# resize img without interpolation (want the image to still match
# label_img, which we resize below):
img = cv2.resize(img, (new_img_w, new_img_h),
interpolation=cv2.INTER_NEAREST) # (shape: (new_img_h, new_img_w, 3))
# resize label_img without interpolation (want the resulting image to
# still only contain pixel values corresponding to an object class):
label_img = cv2.resize(label_img, (new_img_w, new_img_h),
interpolation=cv2.INTER_NEAREST) # (shape: (new_img_h, new_img_w))
########################################################################
# # # # # # # # debug visualization START
# print (scale)
# print (new_img_h)
# print (new_img_w)
#
# cv2.imshow("test", img)
# cv2.waitKey(0)
#
# cv2.imshow("test", label_img)
# cv2.waitKey(0)
# # # # # # # # debug visualization END
########################################################################
# select a 256x256 random crop from the img and label:
########################################################################
start_x = np.random.randint(low=0, high=(new_img_w - 256))
end_x = start_x + 256
start_y = np.random.randint(low=0, high=(new_img_h - 256))
end_y = start_y + 256
img = img[start_y:end_y, start_x:end_x] # (shape: (256, 256, 3))
label_img = label_img[start_y:end_y, start_x:end_x] # (shape: (256, 256))
########################################################################
# # # # # # # # debug visualization START
# print (img.shape)
# print (label_img.shape)
#
# cv2.imshow("test", img)
# cv2.waitKey(0)
#
# cv2.imshow("test", label_img)
# cv2.waitKey(0)
# # # # # # # # debug visualization END
# normalize the img (with the mean and std for the pretrained ResNet):
img = img/255.0
img = img - np.array([0.485, 0.456, 0.406])
img = img/np.array([0.229, 0.224, 0.225]) # (shape: (256, 256, 3))
img = np.transpose(img, (2, 0, 1)) # (shape: (3, 256, 256))
img = img.astype(np.float32)
# convert numpy -> torch:
img = torch.from_numpy(img) # (shape: (3, 256, 256))
label_img = torch.from_numpy(label_img) # (shape: (256, 256))
return (img, label_img)
def __len__(self):
return self.num_examples
class DatasetVal(torch.utils.data.Dataset):
def __init__(self, cityscapes_data_path, cityscapes_meta_path):
self.img_dir = cityscapes_data_path + "/leftImg8bit/val/"
self.label_dir = cityscapes_meta_path + "/label_imgs/"
self.img_h = 1024
self.img_w = 2048
self.new_img_h = 512
self.new_img_w = 1024
self.examples = []
for val_dir in val_dirs:
val_img_dir_path = self.img_dir + val_dir
file_names = os.listdir(val_img_dir_path)
for file_name in file_names:
img_id = file_name.split("_leftImg8bit.png")[0]
img_path = val_img_dir_path + file_name
label_img_path = self.label_dir + img_id + ".png"
label_img = cv2.imread(label_img_path, -1) # (shape: (1024, 2048))
example = {}
example["img_path"] = img_path
example["label_img_path"] = label_img_path
example["img_id"] = img_id
self.examples.append(example)
self.num_examples = len(self.examples)
def __getitem__(self, index):
example = self.examples[index]
img_id = example["img_id"]
img_path = example["img_path"]
img = cv2.imread(img_path, -1) # (shape: (1024, 2048, 3))
# resize img without interpolation (want the image to still match
# label_img, which we resize below):
img = cv2.resize(img, (self.new_img_w, self.new_img_h),
interpolation=cv2.INTER_NEAREST) # (shape: (512, 1024, 3))
label_img_path = example["label_img_path"]
label_img = cv2.imread(label_img_path, -1) # (shape: (1024, 2048))
# resize label_img without interpolation (want the resulting image to
# still only contain pixel values corresponding to an object class):
label_img = cv2.resize(label_img, (self.new_img_w, self.new_img_h),
interpolation=cv2.INTER_NEAREST) # (shape: (512, 1024))
# # # # # # # # debug visualization START
# cv2.imshow("test", img)
# cv2.waitKey(0)
#
# cv2.imshow("test", label_img)
# cv2.waitKey(0)
# # # # # # # # debug visualization END
# normalize the img (with the mean and std for the pretrained ResNet):
img = img/255.0
img = img - np.array([0.485, 0.456, 0.406])
img = img/np.array([0.229, 0.224, 0.225]) # (shape: (512, 1024, 3))
img = np.transpose(img, (2, 0, 1)) # (shape: (3, 512, 1024))
img = img.astype(np.float32)
# convert numpy -> torch:
img = torch.from_numpy(img) # (shape: (3, 512, 1024))
label_img = torch.from_numpy(label_img) # (shape: (512, 1024))
return (img, label_img, img_id)
def __len__(self):
return self.num_examples
class DatasetSeq(torch.utils.data.Dataset):
def __init__(self, cityscapes_data_path, cityscapes_meta_path, sequence):
self.img_dir = cityscapes_data_path + "/leftImg8bit/demoVideo/stuttgart_" + sequence + "/"
self.img_h = 1024
self.img_w = 2048
self.new_img_h = 512
self.new_img_w = 1024
self.examples = []
file_names = os.listdir(self.img_dir)
for file_name in file_names:
img_id = file_name.split("_leftImg8bit.png")[0]
img_path = self.img_dir + file_name
example = {}
example["img_path"] = img_path
example["img_id"] = img_id
self.examples.append(example)
self.num_examples = len(self.examples)
def __getitem__(self, index):
example = self.examples[index]
img_id = example["img_id"]
img_path = example["img_path"]
img = cv2.imread(img_path, -1) # (shape: (1024, 2048, 3))
# resize img without interpolation:
img = cv2.resize(img, (self.new_img_w, self.new_img_h),
interpolation=cv2.INTER_NEAREST) # (shape: (512, 1024, 3))
# normalize the img (with the mean and std for the pretrained ResNet):
img = img/255.0
img = img - np.array([0.485, 0.456, 0.406])
img = img/np.array([0.229, 0.224, 0.225]) # (shape: (512, 1024, 3))
img = np.transpose(img, (2, 0, 1)) # (shape: (3, 512, 1024))
img = img.astype(np.float32)
# convert numpy -> torch:
img = torch.from_numpy(img) # (shape: (3, 512, 1024))
return (img, img_id)
def __len__(self):
return self.num_examples
class DatasetThnSeq(torch.utils.data.Dataset):
def __init__(self, thn_data_path):
self.img_dir = thn_data_path + "/"
self.examples = []
file_names = os.listdir(self.img_dir)
for file_name in file_names:
img_id = file_name.split(".png")[0]
img_path = self.img_dir + file_name
example = {}
example["img_path"] = img_path
example["img_id"] = img_id
self.examples.append(example)
self.num_examples = len(self.examples)
def __getitem__(self, index):
example = self.examples[index]
img_id = example["img_id"]
img_path = example["img_path"]
img = cv2.imread(img_path, -1) # (shape: (512, 1024, 3))
# normalize the img (with mean and std for the pretrained ResNet):
img = img/255.0
img = img - np.array([0.485, 0.456, 0.406])
img = img/np.array([0.229, 0.224, 0.225]) # (shape: (512, 1024, 3))
img = np.transpose(img, (2, 0, 1)) # (shape: (3, 512, 1024))
img = img.astype(np.float32)
# convert numpy -> torch:
img = torch.from_numpy(img) # (shape: (3, 512, 1024))
return (img, img_id)
def __len__(self):
return self.num_examples