-
Notifications
You must be signed in to change notification settings - Fork 1
/
data.py
381 lines (320 loc) · 14.3 KB
/
data.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
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Modified from https://github.com/FlyingGiraffe/vnn-pc
"""
import os
import sys
import glob
import h5py
import numpy as np
import torch
from torch.utils.data import Dataset
def pc_normalize(pc):
centroid = np.mean(pc, axis=0)
pc = pc - centroid
m = np.max(np.sqrt(np.sum(pc**2, axis=1)))
pc = pc / m
return pc
def download_modelnet40():
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
DATA_DIR = os.path.join(BASE_DIR, 'data')
if not os.path.exists(DATA_DIR):
os.mkdir(DATA_DIR)
if not os.path.exists(os.path.join(DATA_DIR, 'modelnet40_ply_hdf5_2048')):
www = 'https://shapenet.cs.stanford.edu/media/modelnet40_ply_hdf5_2048.zip'
zipfile = os.path.basename(www)
os.system('wget %s --no-check-certificate; unzip %s' % (www, zipfile))
os.system('mv %s %s' % (zipfile[:-4], DATA_DIR))
os.system('rm %s' % (zipfile))
def download_shapenetpart():
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
DATA_DIR = os.path.join(BASE_DIR, 'data')
if not os.path.exists(DATA_DIR):
os.mkdir(DATA_DIR)
if not os.path.exists(os.path.join(DATA_DIR, 'shapenet_part_seg_hdf5_data')):
www = 'https://shapenet.cs.stanford.edu/media/shapenet_part_seg_hdf5_data.zip'
zipfile = os.path.basename(www)
os.system('wget %s --no-check-certificate; unzip %s' % (www, zipfile))
os.system('mv %s %s' % (zipfile[:-4], os.path.join(DATA_DIR, 'shapenet_part_seg_hdf5_data')))
os.system('rm %s' % (zipfile))
def download_S3DIS():
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
DATA_DIR = os.path.join(BASE_DIR, 'data')
if not os.path.exists(DATA_DIR):
os.mkdir(DATA_DIR)
if not os.path.exists(os.path.join(DATA_DIR, 'indoor3d_sem_seg_hdf5_data')):
www = 'https://shapenet.cs.stanford.edu/media/indoor3d_sem_seg_hdf5_data.zip'
zipfile = os.path.basename(www)
os.system('wget %s; unzip %s' % (www, zipfile))
os.system('mv %s %s' % (zipfile[:-4], DATA_DIR))
os.system('rm %s' % (zipfile))
if not os.path.exists(os.path.join(DATA_DIR, 'Stanford3dDataset_v1.2_Aligned_Version')):
if not os.path.exists(os.path.join(DATA_DIR, 'Stanford3dDataset_v1.2_Aligned_Version.zip')):
print('Please download Stanford3dDataset_v1.2_Aligned_Version.zip \
from https://goo.gl/forms/4SoGp4KtH1jfRqEj2 and place it under data/')
sys.exit(0)
else:
zippath = os.path.join(DATA_DIR, 'Stanford3dDataset_v1.2_Aligned_Version.zip')
os.system('unzip %s' % (zippath))
os.system('rm %s' % (zippath))
def load_data_cls(data_dir, partition):
#download_modelnet40()
#BASE_DIR = os.path.dirname(os.path.abspath(__file__))
#DATA_DIR = os.path.join(BASE_DIR, 'data')
DATA_DIR = data_dir
all_data = []
all_label = []
for h5_name in glob.glob(os.path.join(DATA_DIR, 'modelnet40*hdf5_2048', '*%s*.h5'%partition)):
f = h5py.File(h5_name)
data = f['data'][:].astype('float32')
label = f['label'][:].astype('int64')
f.close()
all_data.append(data)
all_label.append(label)
all_data = np.concatenate(all_data, axis=0)
all_label = np.concatenate(all_label, axis=0)
return all_data, all_label
def load_data_partseg(data_dir, partition):
#download_shapenetpart()
#BASE_DIR = os.path.dirname(os.path.abspath(__file__))
#DATA_DIR = os.path.join(BASE_DIR, 'data')
DATA_DIR = data_dir
all_data = []
all_label = []
all_seg = []
if partition == 'trainval':
file = glob.glob(os.path.join(DATA_DIR, 'shapenet*hdf5*', '*train*.h5')) \
+ glob.glob(os.path.join(DATA_DIR, 'shapenet*hdf5*', '*val*.h5'))
else:
file = glob.glob(os.path.join(DATA_DIR, 'shapenet*hdf5*', '*%s*.h5'%partition))
for h5_name in file:
f = h5py.File(h5_name, 'r+')
data = f['data'][:].astype('float32')
label = f['label'][:].astype('int64')
seg = f['pid'][:].astype('int64')
f.close()
all_data.append(data)
all_label.append(label)
all_seg.append(seg)
all_data = np.concatenate(all_data, axis=0)
all_label = np.concatenate(all_label, axis=0)
all_seg = np.concatenate(all_seg, axis=0)
return all_data, all_label, all_seg
def prepare_test_data_semseg():
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
DATA_DIR = os.path.join(BASE_DIR, 'data')
if not os.path.exists(os.path.join(DATA_DIR, 'stanford_indoor3d')):
os.system('python prepare_data/collect_indoor3d_data.py')
if not os.path.exists(os.path.join(DATA_DIR, 'indoor3d_sem_seg_hdf5_data_test')):
os.system('python prepare_data/gen_indoor3d_h5.py')
def load_data_semseg(partition, test_area):
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
DATA_DIR = os.path.join(BASE_DIR, 'data')
download_S3DIS()
prepare_test_data_semseg()
if partition == 'train':
data_dir = os.path.join(DATA_DIR, 'indoor3d_sem_seg_hdf5_data')
else:
data_dir = os.path.join(DATA_DIR, 'indoor3d_sem_seg_hdf5_data_test')
with open(os.path.join(data_dir, "all_files.txt")) as f:
all_files = [line.rstrip() for line in f]
with open(os.path.join(data_dir, "room_filelist.txt")) as f:
room_filelist = [line.rstrip() for line in f]
data_batchlist, label_batchlist = [], []
for f in all_files:
file = h5py.File(os.path.join(DATA_DIR, f), 'r+')
data = file["data"][:]
label = file["label"][:]
data_batchlist.append(data)
label_batchlist.append(label)
data_batches = np.concatenate(data_batchlist, 0)
seg_batches = np.concatenate(label_batchlist, 0)
test_area_name = "Area_" + test_area
train_idxs, test_idxs = [], []
for i, room_name in enumerate(room_filelist):
if test_area_name in room_name:
test_idxs.append(i)
else:
train_idxs.append(i)
if partition == 'train':
all_data = data_batches[train_idxs, ...]
all_seg = seg_batches[train_idxs, ...]
else:
all_data = data_batches[test_idxs, ...]
all_seg = seg_batches[test_idxs, ...]
return all_data, all_seg
def translate_pointcloud(pointcloud):
xyz1 = np.random.uniform(low=2./3., high=3./2., size=[3])
xyz2 = np.random.uniform(low=-0.2, high=0.2, size=[3])
translated_pointcloud = np.add(np.multiply(pointcloud, xyz1), xyz2).astype('float32')
return translated_pointcloud
def jitter_pointcloud(pointcloud, sigma=0.01, clip=0.02):
N, C = pointcloud.shape
pointcloud += np.clip(sigma * np.random.randn(N, C), -1*clip, clip)
return pointcloud
def rotate_pointcloud(pointcloud):
theta = np.pi*2 * np.random.uniform()
rotation_matrix = np.array([[np.cos(theta), -np.sin(theta)],[np.sin(theta), np.cos(theta)]])
pointcloud[:,[0,2]] = pointcloud[:,[0,2]].dot(rotation_matrix) # random rotation (x,z)
return pointcloud
class ModelNet40(Dataset):
def __init__(self, num_points, data_dir, partition='train', **kwargs):
self.data, self.label = load_data_cls(data_dir, partition)
self.num_points = num_points
self.partition = partition
def __getitem__(self, item):
pointcloud = self.data[item][:self.num_points]
label = self.label[item]
if self.partition == 'train':
pointcloud = translate_pointcloud(pointcloud)
np.random.shuffle(pointcloud)
return pointcloud, label
def __len__(self):
return self.data.shape[0]
class ModelNet40_v2(Dataset):
def __init__(self, data_dir, num_points=1024, partition='train', uniform=False, normal_channel=False, cache_size=15000):
self.root = data_dir
self.npoints = num_points
self.uniform = uniform
self.catfile = os.path.join(self.root, 'modelnet40_shape_names.txt')
split = partition
self.cat = [line.rstrip() for line in open(self.catfile)]
self.classes = dict(zip(self.cat, range(len(self.cat))))
self.normal_channel = normal_channel
shape_ids = {}
shape_ids['train'] = [line.rstrip() for line in open(os.path.join(self.root, 'modelnet40_train.txt'))]
shape_ids['test'] = [line.rstrip() for line in open(os.path.join(self.root, 'modelnet40_test.txt'))]
assert (split == 'train' or split == 'test')
shape_names = ['_'.join(x.split('_')[0:-1]) for x in shape_ids[split]]
# list of (shape_name, shape_txt_file_path) tuple
self.datapath = [(shape_names[i], os.path.join(self.root, shape_names[i], shape_ids[split][i]) + '.txt') for i
in range(len(shape_ids[split]))]
print('The size of %s data is %d'%(split,len(self.datapath)))
self.cache_size = cache_size # how many data points to cache in memory
self.cache = {} # from index to (point_set, cls) tuple
def __len__(self):
return len(self.datapath)
def _get_item(self, index):
if index in self.cache:
point_set, cls = self.cache[index]
else:
fn = self.datapath[index]
cls = self.classes[self.datapath[index][0]]
cls = np.array([cls]).astype(np.int32)
point_set = np.loadtxt(fn[1], delimiter=',').astype(np.float32)
if self.uniform:
point_set = farthest_point_sample(point_set, self.npoints)
else:
point_set = point_set[0:self.npoints,:]
point_set[:, 0:3] = pc_normalize(point_set[:, 0:3])
if not self.normal_channel:
point_set = point_set[:, 0:3]
if len(self.cache) < self.cache_size:
self.cache[index] = (point_set, cls)
return point_set, cls
def __getitem__(self, index):
return self._get_item(index)
class ShapeNetPart(Dataset):
def __init__(self, num_points, data_dir, partition='train', class_choice=None):
self.data, self.label, self.seg = load_data_partseg(data_dir, partition)
self.cat2id = {'airplane': 0, 'bag': 1, 'cap': 2, 'car': 3, 'chair': 4,
'earphone': 5, 'guitar': 6, 'knife': 7, 'lamp': 8, 'laptop': 9,
'motor': 10, 'mug': 11, 'pistol': 12, 'rocket': 13, 'skateboard': 14, 'table': 15}
self.seg_num = [4, 2, 2, 4, 4, 3, 3, 2, 4, 2, 6, 2, 3, 3, 3, 3]
self.index_start = [0, 4, 6, 8, 12, 16, 19, 22, 24, 28, 30, 36, 38, 41, 44, 47]
self.num_points = num_points
self.partition = partition
self.class_choice = class_choice
if self.class_choice != None:
id_choice = self.cat2id[self.class_choice]
indices = (self.label == id_choice).squeeze()
self.data = self.data[indices]
self.label = self.label[indices]
self.seg = self.seg[indices]
self.seg_num_all = self.seg_num[id_choice]
self.seg_start_index = self.index_start[id_choice]
else:
self.seg_num_all = 50
self.seg_start_index = 0
def __getitem__(self, item):
pointcloud = self.data[item][:self.num_points]
label = self.label[item]
seg = self.seg[item][:self.num_points]
if self.partition == 'trainval':
# pointcloud = translate_pointcloud(pointcloud)
indices = list(range(pointcloud.shape[0]))
np.random.shuffle(indices)
pointcloud = pointcloud[indices]
seg = seg[indices]
return pointcloud, label, seg
def __len__(self):
return self.data.shape[0]
class ScanObjectNNCls(Dataset):
def __init__(self, num_points, data_dir, partition='train', subset='easy'):
super().__init__()
self.partition = partition
if self.partition == 'train':
if subset == 'easy':
data_path = os.path.join(data_dir, 'h5_files', 'main_split', 'training_objectdataset.h5')
else:
data_path = os.path.join(data_dir, 'h5_files', 'main_split', 'training_objectdataset_augmentedrot_scale75.h5')
elif self.partition == 'test':
if subset == 'easy':
data_path = os.path.join(data_dir, 'h5_files', 'main_split', 'test_objectdataset.h5')
else:
data_path = os.path.join(data_dir, 'h5_files', 'main_split', 'test_objectdataset_augmentedrot_scale75.h5')
else:
raise ValueError('not recognized partition {}'.format(self.partition))
h5 = h5py.File(data_path, 'r')
self.points = np.array(h5['data']).astype('float32')
self.labels = np.array(h5['label']).astype('int64')
h5.close()
self.num_points = num_points
self.partition = partition
print('Successfully loaded ScanObjectNN with', len(self.labels), 'instances')
def __getitem__(self, idx):
pt_idxs = np.arange(0, self.points.shape[1]) # 2048
np.random.shuffle(pt_idxs)
pt_idxs = pt_idxs[:self.num_points]
pointcloud = self.points[idx, pt_idxs].copy()
if self.partition == 'train':
pointcloud = translate_pointcloud(pointcloud)
label = self.labels[idx]
return pointcloud, label
def __len__(self):
return self.points.shape[0]
class S3DIS(Dataset):
def __init__(self, num_points=4096, partition='train', test_area='1'):
self.data, self.seg = load_data_semseg(partition, test_area)
self.num_points = num_points
self.partition = partition
def __getitem__(self, item):
pointcloud = self.data[item][:self.num_points]
seg = self.seg[item][:self.num_points]
if self.partition == 'train':
indices = list(range(pointcloud.shape[0]))
np.random.shuffle(indices)
pointcloud = pointcloud[indices]
seg = seg[indices]
seg = torch.LongTensor(seg)
return pointcloud, seg
def __len__(self):
return self.data.shape[0]
if __name__ == '__main__':
train = ModelNet40(1024)
test = ModelNet40(1024, 'test')
data, label = train[0]
print(data.shape)
print(label.shape)
trainval = ShapeNetPart(2048, 'trainval')
test = ShapeNetPart(2048, 'test')
data, label, seg = trainval[0]
print(data.shape)
print(label.shape)
print(seg.shape)
train = S3DIS(4096)
test = S3DIS(4096, 'test')
data, seg = train[0]
print(data.shape)
print(seg.shape)