抽取modelnet40_ply_hdf5_2048数据集的子类集制作h5点云

夜晓岚渺渺

已于 2022-04-20 22:06:00 修改

阅读量5.5k

点赞数 6

分类专栏：点云 tensorflow学习 python 文章标签： python 点云

于 2020-08-15 15:56:02 首次发布

本文链接：https://blog.csdn.net/kkxi123456/article/details/108023763

版权

python 同时被 3 个专栏收录

31 篇文章 1 订阅

订阅专栏

tensorflow学习

24 篇文章 0 订阅

订阅专栏

点云

12 篇文章 1 订阅

订阅专栏

本文参考: 用modelnet40_ply_hdf5_2048数据集制作txt点云数据集（抽取特定类别）_好好学习嘻嘻的博客-CSDN博客

最近要做modelnet10的分类问题，发现网上没有modelnet10的hd5文件资源，自己使用off文件又不会制作，那就使用modelnet40_ply_hdf5_2048制作我们的modelnet10_ply_hdf5_2048文件吧。只看到有人使用modelnet40_ply_hdf5_2048制作了每个点云的txt文档，具体如何制作hd5文件没有其他的资料。本文简单的制作了一下，如有不对的地方，欢迎指正。

modelnet40_ply_hdf5_2048数据集下载地址为:https://shapenet.cs.stanford.edu/media/modelnet40_ply_hdf5_2048.zip

打开和创建 h5py 文件

新建一个hdf5文件，文件名是tutorial.h5，写的模式，描述为test file。

f = open_file('tutorial.h5',mode='w',title='test file')

HDF5 文件通常像标准 Python 文件对象一样工作。它们支持 r / w / a 等标准模式，并且在不再使用时应关闭。但是，显然没有“text”与“binary”模式的概念。

文件名可以是字节字符串或 unicode 字符串。有效mode是：

mode	说明
r	只读，文件必须存在
r+	读 / 写，文件必须存在
w	创建文件，已经存在的文件会被覆盖掉
w- / x	创建文件，文件如果已经存在则出错
a	打开已经存在的文件进行读 / 写，如果不存在则创建一个新文件读 / 写（默认）

在当前目录下会生成一个 myh5py.hdf5 文件

import os
import sys
import numpy as np
import h5py
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
sys.path.clear()
sys.path.append(BASE_DIR)
print(sys.path)
print(BASE_DIR)

# label2sub_class = (1, 2, 3, 4, 5, 6, 7, 8, 9)
label2sub_class = (2, 4, 8, 12, 14, 19, 28, 30, 33, 38)


def getDataFiles(list_filename):
    return [line.rstrip() for line in open(list_filename)]


def load_h5(h5_filename):
    h5f = h5py.File(h5_filename)
    data = h5f['data'][:]
    label = h5f['label'][:]
    normal = h5f['normal'][:]
    return data, label, normal


def loadDataFile(filename):
    return load_h5(filename)


# 写入文件
def write_data2h5(file_name, label, h5data, h5normal):
    h5f = h5py.File(file_name, 'w')
    h5f['label'] = label
    h5f['data'] = h5data
    h5f['normal'] = h5normal
    h5f.close()
    # h5f.create_dataset(label, data=h5data)


# 由于 train_files 的路径设定为 .../data/modelnet40_ply_hdf5_2048/...',在这里我们不做修改
TRAIN_FILES = getDataFiles(os.path.join(BASE_DIR, 'data/modelnet40_ply_hdf5_2048/train_files.txt'))
TEST_FILES = getDataFiles(os.path.join(BASE_DIR, 'data/modelnet40_ply_hdf5_2048/test_files.txt'))

# 本人的存储路径，modelnet40_ply_hdf5_2048有5个train文件，在这里也是5个。两个test文件，本人如是
# ...//data/mydata/...为本人存放数据的路径
filename_train0 = BASE_DIR + '/data/mydata/ply_data_train0.h5'  # 创建点云的路径
filename_train1 = BASE_DIR + '/data/mydata/ply_data_train1.h5'  # 创建点云的路径
filename_train2 = BASE_DIR + '/data/mydata/ply_data_train2.h5'  # 创建点云的路径
filename_train3 = BASE_DIR + '/data/mydata/ply_data_train3.h5'  # 创建点云的路径
filename_train4 = BASE_DIR + '/data/mydata/ply_data_train4.h5'  # 创建点云的路径

filename_test0 = BASE_DIR + '/data/mydata/ply_data_test0.h5'  # 创建点云的路径
filename_test1 = BASE_DIR + '/data/mydata/ply_data_test1.h5'  # 创建点云的路径

file_length2train = len(TRAIN_FILES)
file_length2test = len(TEST_FILES)

label_list2sub_class = []
data_list2sub_class = []
normal_list2sub_class = []
for fn in range(len(TRAIN_FILES)):
    current_data, current_label, current_normal = loadDataFile(TRAIN_FILES[fn])
    current_label = np.squeeze(current_label)
    label_length = len(current_label)
    if fn == 0:
        for j in range(label_length):
            label = current_label[j]
            if label in label2sub_class:
                data = current_data[j]
                normal = current_normal[j]
                label_list2sub_class.append(current_label[j])
                data_list2sub_class.append(current_data[j])
                normal_list2sub_class.append(current_normal[j])
        write_data2h5(filename_train0, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
        label_list2sub_class.clear()
        data_list2sub_class.clear()
        normal_list2sub_class.clear()
    elif fn == 1:
        for j in range(label_length):
            label = current_label[j]
            if label in label2sub_class:
                label_list2sub_class.append(current_label[j])
                data_list2sub_class.append(current_data[j])
                normal_list2sub_class.append(current_normal[j])
        write_data2h5(filename_train1, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
        label_list2sub_class.clear()
        data_list2sub_class.clear()
        normal_list2sub_class.clear()
    elif fn == 2:
        for j in range(label_length):
            label = current_label[j]
            if label in label2sub_class:
                label_list2sub_class.append(current_label[j])
                data_list2sub_class.append(current_data[j])
                normal_list2sub_class.append(current_normal[j])
        write_data2h5(filename_train2, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
        label_list2sub_class.clear()
        data_list2sub_class.clear()
        normal_list2sub_class.clear()
    elif fn == 3:
        for j in range(label_length):
            label = current_label[j]
            if label in label2sub_class:
                label_list2sub_class.append(current_label[j])
                data_list2sub_class.append(current_data[j])
                normal_list2sub_class.append(current_normal[j])
        write_data2h5(filename_train3, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
        label_list2sub_class.clear()
        data_list2sub_class.clear()
        normal_list2sub_class.clear()
    elif fn == 4:
        for j in range(label_length):
            label = current_label[j]
            if label in label2sub_class:
                label_list2sub_class.append(current_label[j])
                data_list2sub_class.append(current_data[j])
                normal_list2sub_class.append(current_normal[j])
        write_data2h5(filename_train4, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
        label_list2sub_class.clear()
        data_list2sub_class.clear()
        normal_list2sub_class.clear()


for fn in range(len(TEST_FILES)):
    current_data, current_label, current_normal=loadDataFile(TEST_FILES[fn])
    current_label = np.squeeze(current_label)
    label_length2test = len(current_label)
    if fn == 0:
        for j in range(label_length2test):
            label = current_label[j]
            if label in label2sub_class:
                label_list2sub_class.append(current_label[j])
                data_list2sub_class.append(current_data[j])
                normal_list2sub_class.append(current_normal[j])
        write_data2h5(filename_test0, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
        label_list2sub_class.clear()
        data_list2sub_class.clear()
        normal_list2sub_class.clear()
    else:
        for j in range(label_length2test):
            label = current_label[j]
            if label in label2sub_class:
                label_list2sub_class.append(current_label[j])
                data_list2sub_class.append(current_data[j])
                normal_list2sub_class.append(current_normal[j])
        write_data2h5(filename_test1, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
        label_list2sub_class.clear()
        data_list2sub_class.clear()
        normal_list2sub_class.clear()

上面的代码比较冗长，low了点，本人就不删了，便于理解，下面为简洁的。

import os
import sys
import numpy as np
import h5py
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
sys.path.clear()
sys.path.append(BASE_DIR)
print(sys.path)
print(BASE_DIR)

# label2sub_class = (1, 2, 3, 4, 5, 6, 7, 8, 9)
label2sub_class = (2, 4, 8, 12, 14, 19, 28, 30, 33, 38)


def getDataFiles(list_filename):
    return [line.rstrip() for line in open(list_filename)]


def load_h5(h5_filename):
    h5f = h5py.File(h5_filename)
    data = h5f['data'][:]
    label = h5f['label'][:]
    normal = h5f['normal'][:]
    return data, label, normal


def loadDataFile(filename):
    return load_h5(filename)


# 写入文件
def write_data2h5(file_name, label, h5data, h5normal):
    h5f = h5py.File(file_name, 'w')
    h5f['label'] = label
    h5f['data'] = h5data
    h5f['normal'] = h5normal
    h5f.close()
    # h5f.create_dataset(label, data=h5data)


# 由于 train_files 的路径设定为 .../data/modelnet40_ply_hdf5_2048/...',在这里我们不做修改
TRAIN_FILES = getDataFiles(os.path.join(BASE_DIR, 'data/modelnet40_ply_hdf5_2048/train_files.txt'))
TEST_FILES = getDataFiles(os.path.join(BASE_DIR, 'data/modelnet40_ply_hdf5_2048/test_files.txt'))

# 本人的存储路径，modelnet40_ply_hdf5_2048有5个train文件，在这里也是5个。两个test文件，本人如是
# ...//data/mydata/...为本人存放数据的路径
filename_train0 = BASE_DIR + '/data/mydata/ply_data_train0.h5'  # 创建点云的路径
filename_train1 = BASE_DIR + '/data/mydata/ply_data_train1.h5'  # 创建点云的路径
filename_train2 = BASE_DIR + '/data/mydata/ply_data_train2.h5'  # 创建点云的路径
filename_train3 = BASE_DIR + '/data/mydata/ply_data_train3.h5'  # 创建点云的路径
filename_train4 = BASE_DIR + '/data/mydata/ply_data_train4.h5'  # 创建点云的路径

filename_test0 = BASE_DIR + '/data/mydata/ply_data_test0.h5'  # 创建点云的路径
filename_test1 = BASE_DIR + '/data/mydata/ply_data_test1.h5'  # 创建点云的路径

file_length2train = len(TRAIN_FILES)
file_length2test = len(TEST_FILES)

label_list2sub_class = []
data_list2sub_class = []
normal_list2sub_class = []
for fn in range(len(TRAIN_FILES)):
    current_data, current_label, current_normal = loadDataFile(TRAIN_FILES[fn])
    current_label = np.squeeze(current_label)
    label_length = len(current_label)
    for j in range(label_length):
        label = current_label[j]
        if label in label2sub_class:
            data = current_data[j]
            normal = current_normal[j]
            label_list2sub_class.append(current_label[j])
            data_list2sub_class.append(current_data[j])
            normal_list2sub_class.append(current_normal[j])
    if fn == 0:
        write_data2h5(filename_train0, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
    elif fn == 1:
        write_data2h5(filename_train1, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
    elif fn == 2:
        write_data2h5(filename_train2, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
    elif fn == 3:
        write_data2h5(filename_train3, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
    elif fn == 4:
        write_data2h5(filename_train4, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
    label_list2sub_class.clear()
    data_list2sub_class.clear()
    normal_list2sub_class.clear()


for fn in range(len(TEST_FILES)):
    current_data, current_label, current_normal=loadDataFile(TEST_FILES[fn])
    current_label = np.squeeze(current_label)
    label_length2test = len(current_label)
    for j in range(label_length2test):
        label = current_label[j]
        if label in label2sub_class:
            label_list2sub_class.append(current_label[j])
            data_list2sub_class.append(current_data[j])
            normal_list2sub_class.append(current_normal[j])
    if fn == 0:
        write_data2h5(filename_test0, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
    else:
        write_data2h5(filename_test1, label_list2sub_class, data_list2sub_class, normal_list2sub_class)
    label_list2sub_class.clear()
    data_list2sub_class.clear()
    normal_list2sub_class.clear()

夜晓岚渺渺

关注

6
点赞
踩
38

收藏

觉得还不错? 一键收藏
5
评论
抽取modelnet40_ply_hdf5_2048数据集的子类集制作h5点云

3.1 打开和创建 h5py 文件新建一个hdf5文件，文件名是tutorial.h5，写的模式，描述为test file。f = open_file('tutorial.h5',mode='w',title='test file')HDF5 文件通常像标准 Python 文件对象一样工作。它们支持 r / w / a 等标准模式，并且在不再使用时应关闭。但是，显然没有“text”与“binary”模式的概念。文件名可以是字节字符串或 unicode 字符串。有效mode是：mod.
复制链接

扫一扫