pointnet provider.loadDataFile

首先看具体实现

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

def loadDataFile(filename):
    return load_h5(filename)

传入的参数是

current_data, current_label = provider.loadDataFile(TRAIN_FILES[train_file_idxs[fn]])
        

其实是对h5py的读取功能进行了封装，传入的是一个h5文件文件名如下

data/modelnet40_ply_hdf5_2048/ply_data_train0.h5
data/modelnet40_ply_hdf5_2048/ply_data_train1.h5
data/modelnet40_ply_hdf5_2048/ply_data_train2.h5
data/modelnet40_ply_hdf5_2048/ply_data_train3.h5
data/modelnet40_ply_hdf5_2048/ply_data_train4.h5

每次在pointnet的工程，train_one_epoch里面每次传入一个

利用h5包中的File函数解析出数据，并提取data以及label作为current_data,和current_label数据源