-
Notifications
You must be signed in to change notification settings - Fork 1
/
data.py
172 lines (145 loc) · 6.71 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
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import os
import glob
import h5py
import numpy as np
from scipy.spatial.transform import Rotation
from torch.utils.data import Dataset
from sklearn.neighbors import NearestNeighbors
from scipy.spatial.distance import minkowski
import copy
def download():
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; unzip %s' % (www, zipfile))
os.system('mv %s %s' % (zipfile[:-4], DATA_DIR))
os.system('rm %s' % (zipfile))
def load_data(partition):
download()
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
DATA_DIR = os.path.join(BASE_DIR,'data')
all_data = []
all_label = []
for h5_name in glob.glob(os.path.join(DATA_DIR, 'modelnet40_ply_hdf5_2048', 'ply_data_%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 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=0.001):
N, C = pointcloud.shape
pointcloud += np.clip(sigma * np.random.randn(N, C), -1 * clip, clip)
return pointcloud
def farthest_subsample_points(pointcloud1, pointcloud2, num_subsampled_points=768):
pointcloud1 = pointcloud1.T
pointcloud2 = pointcloud2.T
num_points = pointcloud1.shape[0]
nbrs1 = NearestNeighbors(n_neighbors=num_subsampled_points, algorithm='auto',
metric=lambda x, y: minkowski(x, y)).fit(pointcloud1)
random_p1 = np.random.random(size=(1, 3)) + np.array([[500, 500, 500]]) * 2
idx1 = nbrs1.kneighbors(random_p1, return_distance=False).reshape((num_subsampled_points,))
nbrs2 = NearestNeighbors(n_neighbors=num_subsampled_points, algorithm='auto',
metric=lambda x, y: minkowski(x, y)).fit(pointcloud2)
random_p2 = np.random.random(size=(1, 3)) + np.array([[-500, -500, -500]]) * 2
idx2 = nbrs2.kneighbors(random_p2, return_distance=False).reshape((num_subsampled_points,))
return pointcloud1[idx1, :].T, pointcloud2[idx2, :].T
class ModelNet40(Dataset):
def __init__(self, num_points, num_subsampled_points=729, partition='train',
gaussian_noise=False, unseen=False, rot_factor=4, category=None):
super(ModelNet40, self).__init__()
self.data, self.label = load_data(partition)
if category is not None:
self.data = self.data[self.label==category]
self.label = self.label[self.label==category]
self.num_points = num_points
self.num_subsampled_points = num_subsampled_points
self.partition = partition
self.gaussian_noise = gaussian_noise
self.unseen = unseen
self.label = self.label.squeeze()
self.rot_factor = rot_factor
if num_points != num_subsampled_points:
self.subsampled = True
else:
self.subsampled = False
if self.unseen:
if self.partition == 'test':
self.data = self.data[self.label>=20]
self.label = self.label[self.label>=20]
elif self.partition == 'train':
self.data = self.data[self.label<20]
self.label = self.label[self.label<20]
def __getitem__(self, item):
pointcloud = copy.deepcopy(self.data[item][:self.num_points])
if self.partition != 'train':
np.random.seed(item)
anglex = np.random.uniform(-1,1) * np.pi / self.rot_factor
angley = np.random.uniform(-1,1) * np.pi / self.rot_factor
anglez = np.random.uniform(-1,1) * np.pi / self.rot_factor
cosx = np.cos(anglex)
cosy = np.cos(angley)
cosz = np.cos(anglez)
sinx = np.sin(anglex)
siny = np.sin(angley)
sinz = np.sin(anglez)
Rx = np.array([[1, 0, 0],
[0, cosx, -sinx],
[0, sinx, cosx]])
Ry = np.array([[cosy, 0, siny],
[0, 1, 0],
[-siny, 0, cosy]])
Rz = np.array([[cosz, -sinz, 0],
[sinz, cosz, 0],
[0, 0, 1]])
R_ab = Rx.dot(Ry).dot(Rz)
R_ba = R_ab.T
translation_ab = np.array([np.random.uniform(-0.5, 0.5), np.random.uniform(-0.5, 0.5),
np.random.uniform(-0.5, 0.5)])
translation_ba = -R_ba.dot(translation_ab)
pointcloud1 = pointcloud.T
pointcloud2 = copy.deepcopy(pointcloud1)
if self.gaussian_noise != 0:
pointcloud1 = jitter_pointcloud(pointcloud1,clip=self.gaussian_noise)
pointcloud2 = jitter_pointcloud(pointcloud2,clip=self.gaussian_noise)
if self.subsampled:
pointcloud1, pointcloud2 = farthest_subsample_points(pointcloud1, pointcloud2,
num_subsampled_points=self.num_subsampled_points)
rotation_ab = Rotation.from_euler('zyx', [anglez, angley, anglex])
pointcloud2 = rotation_ab.apply(pointcloud2.T).T + np.expand_dims(translation_ab, axis=1)
euler_ab = np.asarray([anglez, angley, anglex]).astype('float32')
euler_ba = -euler_ab[::-1]
index = np.arange(pointcloud2.shape[-1])
index = np.random.permutation(index)
pointcloud2 = pointcloud2.T
pointcloud2 = pointcloud2[index]
pointcloud2 = pointcloud2.T
pcd = {}
Transform = {}
pcd['src'] = pointcloud1.astype('float32')
pcd['tgt'] = pointcloud2.astype('float32')
Transform['R_ab'] = R_ab.astype('float32')
Transform['T_ab'] = translation_ab.astype('float32')
Transform['euler_ab'] = euler_ab.astype('float32')
Transform['R_ba'] = R_ba.astype('float32')
Transform['T_ba'] = translation_ba.astype('float32')
Transform['euler_ba'] = euler_ba.astype('float32')
return pcd, Transform
def __len__(self):
return self.data.shape[0]
if __name__ == '__main__':
print('hello world')