-
Notifications
You must be signed in to change notification settings - Fork 4
/
data.py
223 lines (185 loc) · 8.38 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
import os
import glob
import h5py
import numpy as np
from torch.utils.data import Dataset
import torch
os.environ["HDF5_USE_FILE_LOCKING"] = "FALSE"
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 --no-check-certificate; 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)):
# print(f"h5_name: {h5_name}")
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 random_point_dropout(pc, max_dropout_ratio=0.875):
# ''' batch_pc: BxNx3 '''
# # for b in range(batch_pc.shape[0]):
# dropout_ratio = np.random.random()*max_dropout_ratio # 0~0.875
# drop_idx = np.where(np.random.random((pc.shape[0]))<=dropout_ratio)[0]
# # print ('use random drop', len(drop_idx))
# if len(drop_idx)>0:
# pc[drop_idx,:] = pc[0,:] # set to the first point
# return pc
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 rotate_pointcloud(pointcloud, theta = None):
if theta == None:
theta = np.pi*2 * np.random.rand()
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 PointcloudScale(object): # input random scaling
def __init__(self, scale_low=2. / 3., scale_high=3. / 2.):
self.scale_low = scale_low
self.scale_high = scale_high
def __call__(self, pc):
xyz1 = np.random.uniform(low=self.scale_low, high=self.scale_high, size=[3])
xyz1 = torch.from_numpy(xyz1).float()
pc = torch.from_numpy(pc).float()
pc = torch.mul(pc, xyz1)
return pc
# 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
class ModelNet40(Dataset):
def __init__(self, num_points, partition='train', use_translate = False, use_rotate = False):
self.data, self.label = load_data(partition)
self.num_points = num_points
self.partition = partition
self.use_translate = use_translate
self.use_rotate = use_rotate
def __getitem__(self, item):
pointcloud = self.data[item][:self.num_points]
label = self.label[item]
if self.partition == 'train':
if self.use_translate:
pointcloud = translate_pointcloud(pointcloud)
if self.use_rotate:
pointcloud = rotate_pointcloud(pointcloud)
np.random.shuffle(pointcloud)
return pointcloud, label
def __len__(self):
return self.data.shape[0]
if __name__ == '__main__':
train = ModelNet40(1024)
test = ModelNet40(1024, 'test')
for data, label in train:
print(data.shape)
print(label.shape)
# from torch.utils.data import DataLoader
# train_loader = DataLoader(ModelNet40(partition='train', num_points=1024), num_workers=4,
# batch_size=32, shuffle=True, drop_last=True)
# for batch_idx, (data, label) in enumerate(train_loader):
# print(f"batch_idx: {batch_idx} | data shape: {data.shape} | ;lable shape: {label.shape}")
# train_set = ModelNet40(partition='train', num_points=1024)
# test_set = ModelNet40(partition='test', num_points=1024)
# print(f"train_set size {train_set.__len__()}")
# print(f"test_set size {test_set.__len__()}")
# import os
# import glob
# import h5py
# import numpy as np
# from torch.utils.data import Dataset
# os.environ["HDF5_USE_FILE_LOCKING"] = "FALSE"
# 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 --no-check-certificate; 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)):
# # print(f"h5_name: {h5_name}")
# 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 random_point_dropout(pc, max_dropout_ratio=0.875):
# ''' batch_pc: BxNx3 '''
# # for b in range(batch_pc.shape[0]):
# dropout_ratio = np.random.random()*max_dropout_ratio # 0~0.875
# drop_idx = np.where(np.random.random((pc.shape[0]))<=dropout_ratio)[0]
# # print ('use random drop', len(drop_idx))
# if len(drop_idx)>0:
# pc[drop_idx,:] = pc[0,:] # set to the first point
# return pc
# 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
# class ModelNet40(Dataset):
# def __init__(self, num_points, partition='train'):
# self.data, self.label = load_data(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 = random_point_dropout(pointcloud) # open for dgcnn not for our idea for all
# pointcloud = translate_pointcloud(pointcloud)
# np.random.shuffle(pointcloud)
# return pointcloud, label
# def __len__(self):
# return self.data.shape[0]
# if __name__ == '__main__':
# train = ModelNet40(1024)
# test = ModelNet40(1024, 'test')
# # for data, label in train:
# # print(data.shape)
# # print(label.shape)
# from torch.utils.data import DataLoader
# train_loader = DataLoader(ModelNet40(partition='train', num_points=1024), num_workers=4,
# batch_size=32, shuffle=True, drop_last=True)
# for batch_idx, (data, label) in enumerate(train_loader):
# print(f"batch_idx: {batch_idx} | data shape: {data.shape} | ;lable shape: {label.shape}")
# train_set = ModelNet40(partition='train', num_points=1024)
# test_set = ModelNet40(partition='test', num_points=1024)
# print(f"train_set size {train_set.__len__()}")
# print(f"test_set size {test_set.__len__()}")