-
Notifications
You must be signed in to change notification settings - Fork 0
/
ModelNetDataset.py
155 lines (130 loc) · 5.71 KB
/
ModelNetDataset.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
# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
# http://www.apache.org/licenses/LICENSE-2.0
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import print_function
import os
import os.path
import paddle
from paddle.io import Dataset
import numpy as np
import sys
from tqdm import tqdm
import json
import pickle
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 farthest_point_sample(point, npoint):
"""
Input:
xyz: pointcloud data, [N, D]
npoint: number of samples
Return:
centroids: sampled pointcloud index, [npoint, D]
"""
N, D = point.shape
xyz = point[:,:3]
centroids = np.zeros((npoint,))
distance = np.ones((N,)) * 1e10
farthest = np.random.randint(0, N)
for i in range(npoint):
centroids[i] = farthest
centroid = xyz[farthest, :]
dist = np.sum((xyz - centroid) ** 2, -1)
mask = dist < distance
distance[mask] = dist[mask]
farthest = np.argmax(distance, -1)
point = point[centroids.astype(np.int32)]
return point
class ModelNetDataset(Dataset):
# 数据读取
"""
Input:
root: 数据集根目录
args: 传入的参数
split: 训练集or测试集
process_data: 预处理数据
"""
def __init__(self,
root,
args,
split='train',
process_data=False):
super(ModelNetDataset, self).__init__()
self.root = root
self.npoints = args.num_point
self.process_data = process_data
self.uniform = args.use_uniform_sample
self.use_normals = args.use_normals
self.num_category = 40
self.catfile = os.path.join(self.root, 'modelnet40_shape_names.txt')
self.cat = [line.rstrip() for line in open(self.catfile)]
self.classes = dict(zip(self.cat, range(len(self.cat))))
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]]
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)))
if self.uniform:
self.save_path = os.path.join(root, 'modelnet%d_%s_%dpts_fps.dat' % (self.num_category, split, self.npoints))
else:
self.save_path = os.path.join(root, 'modelnet%d_%s_%dpts.dat' % (self.num_category, split, self.npoints))
if self.process_data:
if not os.path.exists(self.save_path):
print('Processing data %s (only running in the first time)...' % self.save_path)
self.list_of_points = [None] * len(self.datapath)
self.list_of_labels = [None] * len(self.datapath)
for index in tqdm(range(len(self.datapath)), total=len(self.datapath)):
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, :]
self.list_of_points[index] = point_set
self.list_of_labels[index] = cls
with open(self.save_path, 'wb') as f:
pickle.dump([self.list_of_points, self.list_of_labels], f)
else:
print('Load processed data from %s...' % self.save_path)
with open(self.save_path, 'rb') as f:
self.list_of_points, self.list_of_labels = pickle.load(f)
# else:
# print('Load processed data from %s...' % self.save_path)
# with open(self.save_path, 'rb') as f:
# self.list_of_points, self.list_of_labels = pickle.load(f)
def _get_item(self, index):
if self.process_data:
point_set, label = self.list_of_points[index], self.list_of_labels[index]
else:
fn = self.datapath[index]
cls = self.classes[self.datapath[index][0]]
label = np.array([cls]).astype(np.int64)
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.use_normals:
point_set = point_set[:, 0:3]
return point_set, label[0].astype(np.int64)
def __getitem__(self, index):
return self._get_item(index)
def __len__(self):
return len(self.datapath)