-
Notifications
You must be signed in to change notification settings - Fork 1
/
data.py
202 lines (154 loc) · 6.63 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
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import os
import glob
import h5py
import numpy as np
import torch
from torch.utils.data import Dataset
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' % ('modelnet40_ply_hdf5_2048', DATA_DIR))
os.system('rm %s' % (zipfile))
def load_data_cls(partition):
download_modelnet40()
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', '*%s*.h5' % partition)):
f = h5py.File(h5_name, 'r+')
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_shapenet55():
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
DATA_DIR = os.path.join(BASE_DIR, 'data')
filename = os.path.join(DATA_DIR, 'shapenet57448xyzonly.npz')
data_dict = dict(np.load(filename))
all_data = data_dict['data']
all_index = np.arange(len(all_data))
return all_data, all_index
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, limited_ratio=1.0, partition='train'):
self.data, self.label = load_data_cls(partition)
self.data_size = self.data.shape[0]
self.limited_data_size = int(self.data_size * limited_ratio)
self.data = self.data[:self.limited_data_size]
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 ShapeNet55(Dataset):
def __init__(self, num_points):
self.data, self.index = load_data_shapenet55()
self.num_points = num_points
def __getitem__(self, item):
pointcloud = self.data[item][:self.num_points]
index = self.index[item]
pointcloud = translate_pointcloud(pointcloud)
np.random.shuffle(pointcloud)
return pointcloud, index
def __len__(self):
return self.data.shape[0]
class ScanObjectNN(Dataset):
def __init__(self, num_points, root, partition='train'):
super().__init__()
self.num_points = num_points
self.partition = partition
self.root = root
if self.partition == 'train':
h5 = h5py.File(os.path.join(self.root, 'training_objectdataset.h5'), 'r')
self.points = np.array(h5['data']).astype(np.float32)
self.labels = np.array(h5['label']).astype(int)
h5.close()
elif self.partition == 'test':
h5 = h5py.File(os.path.join(self.root, 'test_objectdataset.h5'), 'r')
self.points = np.array(h5['data']).astype(np.float32)
self.labels = np.array(h5['label']).astype(int)
h5.close()
else:
raise NotImplementedError()
print(f'Successfully load ScanObjectNN shape of {self.points.shape}')
def __getitem__(self, idx):
pt_idxs = np.arange(0, self.num_points)
if self.partition == 'train':
np.random.shuffle(pt_idxs)
current_points = self.points[idx, pt_idxs].copy()
if self.partition == 'train':
current_points = translate_pointcloud(current_points)
# np.random.shuffle(current_points)
current_points = torch.from_numpy(current_points).float()
label = self.labels[idx]
return current_points, label
def __len__(self):
return self.points.shape[0]
class ScanObjectNN_hardest(Dataset):
def __init__(self, num_points, root, partition='train'):
super().__init__()
self.num_points = num_points
self.partition = partition
self.root = root
if self.partition == 'train':
h5 = h5py.File(os.path.join(self.root, 'training_objectdataset_augmentedrot_scale75.h5'), 'r')
self.points = np.array(h5['data']).astype(np.float32)
self.labels = np.array(h5['label']).astype(int)
h5.close()
elif self.partition == 'test':
h5 = h5py.File(os.path.join(self.root, 'test_objectdataset_augmentedrot_scale75.h5'), 'r')
self.points = np.array(h5['data']).astype(np.float32)
self.labels = np.array(h5['label']).astype(int)
h5.close()
else:
raise NotImplementedError()
print(f'Successfully load ScanObjectNN shape of {self.points.shape}')
def __getitem__(self, idx):
pt_idxs = np.arange(0, self.num_points)
if self.partition == 'train':
np.random.shuffle(pt_idxs)
current_points = self.points[idx, pt_idxs].copy()
if self.partition == 'train':
current_points = translate_pointcloud(current_points)
# np.random.shuffle(current_points)
current_points = torch.from_numpy(current_points).float()
label = self.labels[idx]
return current_points, label
def __len__(self):
return self.points.shape[0]
if __name__ == '__main__':
train = ShapeNet55(2048)
data = train[0]
print(data.shape)