This commit is contained in:
Xu Ma 2021-10-04 03:58:19 -04:00
parent 404c207db5
commit eb59980e47
2 changed files with 97 additions and 7 deletions

View file

@ -0,0 +1,96 @@
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__()}")

View file

@ -1,10 +1,4 @@
"""
for training with resume functions.
Usage:
python main.py --model PointNet --msg demo
or
CUDA_VISIBLE_DEVICES=0 nohup python main.py --model PointNet --msg demo > nohup/PointNet_demo.out &
"""
import argparse import argparse
import os import os
import logging import logging