-
Notifications
You must be signed in to change notification settings - Fork 3
/
data.py
139 lines (117 loc) · 5.26 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
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import os
import sys
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
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 --no-check-certificate %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 jitter_pointcloud(pointcloud, sigma=0.01, clip=0.05):
N, C = pointcloud.shape
pointcloud = 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]]) * np.random.choice([1, -1, 1, -1])
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 = random_p1
idx2 = nbrs2.kneighbors(random_p2, return_distance=False).reshape((num_subsampled_points,))
return pointcloud1[idx1, :].T, pointcloud2[idx2, :].T
def random_Rt(angle):
anglex = np.random.uniform() * angle
angley = np.random.uniform() * angle
anglez = np.random.uniform() * angle
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 = Rx.dot(Ry).dot(Rz)
t = np.random.uniform(-0.5, 0.5, size=3)
euler = np.array([anglez, angley, anglex])
return R, t, euler
class ModelNet40(Dataset):
def __init__(self, num_points=1024, partition='train', gaussian_noise=False, alpha=0.75, unseen=False, factor=4):
super(ModelNet40, self).__init__()
self.num_points = num_points
self.partition = partition
self.gaussian_noise = gaussian_noise
self.unseen = unseen
self.rot_factor = factor
if self.unseen:
self.data, self.label = load_data(partition)
self.label = self.label.squeeze()
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]
else:
raise Exception('Invalid partition')
else:
self.data, self.label = load_data(partition)
self.label = self.label.squeeze()
self.data = self.data[:, :self.num_points]
self.num_subsampled_points = int(self.data.shape[1]*alpha)
def __getitem__(self, item):
pointcloud1 = self.data[item].T
R_ab, translation_ab, euler_ab = random_Rt(np.pi/self.rot_factor)
pointcloud2 = np.matmul(R_ab, pointcloud1) + translation_ab[:, np.newaxis]
pointcloud1 = np.random.permutation(pointcloud1.T).T
pointcloud2 = np.random.permutation(pointcloud2.T).T
if self.gaussian_noise:
pointcloud1 = jitter_pointcloud(pointcloud1)
pointcloud2 = jitter_pointcloud(pointcloud2)
pointcloud1, pointcloud2 = farthest_subsample_points(pointcloud1, pointcloud2,
num_subsampled_points=self.num_subsampled_points)
return pointcloud1.astype('float32'), pointcloud2.astype('float32'), R_ab.astype('float32'), \
translation_ab.astype('float32'), euler_ab.astype('float32')
def __len__(self):
return self.data.shape[0]