S3DIS数据集怎么拼接并生成场景npy文件

代码地址：
https://github.com/yanx27/Pointnet_Pointnet2_pytorch/blob/master/data_utils/indoor3d_util.py

S3DIS数据集共有6个area

每个area有多个房间

每个房间内每个物体由单独的文件描述，类别名为文件名

额外的元数据文件：
anno_paths.txt
class_names.txt
从github上下载，分别是每个房间Annotations的文件名列表和数据集的类别名。

代码：

import os
import sys
import glob

import numpy as np

DATA_PATH = '/home/zhy/Dataset/S3DIS/Stanford3dDataset_v1.2_Aligned_Version/'
output_folder = '/home/zhy/Dataset/S3DIS/S3DIS_npy/'


anno_paths = [line.rstrip() for line in open('anno_paths.txt')]
anno_paths = [os.path.join(DATA_PATH, p) for p in anno_paths]

g_classes = [x.rstrip() for x in open('class_names.txt')]
g_class2label = {cls: i for i,cls in enumerate(g_classes)}

if not os.path.exists(output_folder):
    os.mkdir(output_folder)

def collect_point_label(anno_path, out_filename, file_format='txt'):
    """ Convert original dataset files to data_label file (each line is XYZRGBL).
        We aggregated all the points from each instance in the room.

    Args:
        anno_path: path to annotations. e.g. Area_1/office_2/Annotations/
        out_filename: path to save collected points and labels (each line is XYZRGBL)
        file_format: txt or numpy, determines what file format to save.
    Returns:
        None
    Note:
        the points are shifted before save, the most negative point is now at origin.
    """

    points_list = []

    for f in glob.glob(os.path.join(anno_path, '*.txt')):
        cls = os.path.basename(f).split('_')[0]

        if cls not in g_classes: # note: in some room there is 'staris' class..
            cls = 'clutter'
        
        points = np.loadtxt(f)

        labels = np.ones((points.shape[0],1)) * g_class2label[cls]
        points_list.append(np.concatenate([points, labels], 1)) # Nx7

    data_label = np.concatenate(points_list, 0)
    xyz_min = np.amin(data_label, axis=0)[0:3]
    data_label[:, 0:3] -= xyz_min


    if file_format=='txt':
        fout = open(out_filename, 'w')
        for i in range(data_label.shape[0]):
            fout.write('%f %f %f %d %d %d %d\n' % \
                          (data_label[i,0], data_label[i,1], data_label[i,2],
                           data_label[i,3], data_label[i,4], data_label[i,5],
                           data_label[i,6]))
        fout.close()
    elif file_format=='numpy':
        np.save(out_filename, data_label)
    else:
        print('ERROR!! Unknown file format: %s, please use txt or numpy.' % \
            (file_format))
        exit()


# Note: there is an extra character in the v1.2 data in Area_5/hallway_6. It's fixed manually.
for anno_path in anno_paths:
    print(anno_path)
    try:
        elements = anno_path.split('/')
        out_filename = elements[-3]+'_'+elements[-2]+'.npy' # Area_1_hallway_1.npy
        print(out_filename)
        collect_point_label(anno_path, os.path.join(output_folder, out_filename), 'numpy')
    except:
        print(anno_path, 'ERROR!!')

1、读出来每个房间的文件名

anno_paths = [line.rstrip() for line in open('anno_paths.txt')]

2、读出来每个房间的物体的名字

glob.glob(os.path.join(anno_path, '*.txt'))

3、把文件名转换成点的label

labels = np.ones((points.shape[0],1)) * g_class2label[cls]

4、每个房间合并成一个.npy文件

points_list.append(np.concatenate([points, labels], 1))