PointMLP/part_segmentation/data.py
2021-10-04 12:39:33 -04:00

186 lines
6.7 KiB
Python

import os
import sys
import glob
import h5py
import numpy as np
import torch
from torch.utils.data import Dataset
# change this to your data root
DATA_DIR = 'data/'
os.environ["HDF5_USE_FILE_LOCKING"] = "FALSE"
def download_modelnet40():
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')):
os.mkdir(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 download_shapenetpart():
if not os.path.exists(DATA_DIR):
os.mkdir(DATA_DIR)
if not os.path.exists(os.path.join(DATA_DIR)):
os.mkdir(os.path.join(DATA_DIR))
www = 'https://shapenet.cs.stanford.edu/media/shapenet_part_seg_hdf5_data.zip'
zipfile = os.path.basename(www)
os.system('wget %s --no-check-certificate; unzip %s' % (www, zipfile))
os.system('mv %s %s' % (zipfile[:-4], os.path.join(DATA_DIR)))
os.system('rm %s' % (zipfile))
def load_data_normal(partition):
f = h5py.File(os.path.join(DATA_DIR, 'modelnet40_normal', 'normal_%s.h5'%partition), 'r+')
data = f['xyz'][:].astype('float32')
label = f['normal'][:].astype('float32')
f.close()
return data, label
def load_data_cls(partition):
download_modelnet40()
all_data = []
all_label = []
for h5_name in glob.glob(os.path.join(DATA_DIR, 'modelnet40*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_partseg(partition):
download_shapenetpart()
all_data = []
all_label = []
all_seg = []
if partition == 'trainval':
file = glob.glob(os.path.join(DATA_DIR, 'part_segmentation_data', '*train*.h5')) \
+ glob.glob(os.path.join(DATA_DIR, 'part_segmentation_data', '*val*.h5'))
else:
file = glob.glob(os.path.join(DATA_DIR, 'part_segmentation_data', '*%s*.h5'%partition))
for h5_name in file:
f = h5py.File(h5_name, 'r+')
data = f['data'][:].astype('float32')
label = f['label'][:].astype('int64')
seg = f['pid'][:].astype('int64')
f.close()
all_data.append(data)
all_label.append(label)
all_seg.append(seg)
all_data = np.concatenate(all_data, axis=0)
all_label = np.concatenate(all_label, axis=0)
all_seg = np.concatenate(all_seg, axis=0)
return all_data, all_label, all_seg
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, partition='train'):
self.data, self.label = load_data_cls(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 = translate_pointcloud(pointcloud)
#pointcloud = rotate_pointcloud(pointcloud)
np.random.shuffle(pointcloud)
return pointcloud, label
def __len__(self):
return self.data.shape[0]
class ModelNetNormal(Dataset):
def __init__(self, num_points, partition='train'):
self.data, self.label = load_data_normal(partition)
self.num_points = num_points
self.partition = partition
def __getitem__(self, item):
pointcloud = self.data[item][:self.num_points]
label = self.label[item][:self.num_points]
if self.partition == 'train':
#pointcloud = translate_pointcloud(pointcloud)
idx = np.arange(0, pointcloud.shape[0], dtype=np.int64)
np.random.shuffle(idx)
pointcloud = self.data[item][idx]
label = self.label[item][idx]
return pointcloud, label
def __len__(self):
return self.data.shape[0]
class ShapeNetPart(Dataset):
def __init__(self, num_points=2048, partition='train', class_choice=None):
self.data, self.label, self.seg = load_data_partseg(partition)
self.cat2id = {'airplane': 0, 'bag': 1, 'cap': 2, 'car': 3, 'chair': 4,
'earphone': 5, 'guitar': 6, 'knife': 7, 'lamp': 8, 'laptop': 9,
'motor': 10, 'mug': 11, 'pistol': 12, 'rocket': 13, 'skateboard': 14, 'table': 15}
self.seg_num = [4, 2, 2, 4, 4, 3, 3, 2, 4, 2, 6, 2, 3, 3, 3, 3]
self.index_start = [0, 4, 6, 8, 12, 16, 19, 22, 24, 28, 30, 36, 38, 41, 44, 47]
self.num_points = num_points
self.partition = partition
self.class_choice = class_choice
if self.class_choice != None:
id_choice = self.cat2id[self.class_choice]
indices = (self.label == id_choice).squeeze()
self.data = self.data[indices]
self.label = self.label[indices]
self.seg = self.seg[indices]
self.seg_num_all = self.seg_num[id_choice]
self.seg_start_index = self.index_start[id_choice]
else:
self.seg_num_all = 50
self.seg_start_index = 0
def __getitem__(self, item):
pointcloud = self.data[item][:self.num_points]
label = self.label[item]
seg = self.seg[item][:self.num_points]
if self.partition == 'trainval':
pointcloud = translate_pointcloud(pointcloud)
indices = list(range(pointcloud.shape[0]))
np.random.shuffle(indices)
pointcloud = pointcloud[indices]
seg = seg[indices]
return pointcloud, label, seg
def __len__(self):
return self.data.shape[0]