GlottisNetV2 - Time variant training and testing data

Here we provide time variant training and testing data for the GlottisNetV2 study. In particular, this dataset relies on the benchmark for automatic glottis segmentation (BAGLS dataset). This three-dimensional data (time, y, x) is used for experiments involving deep neural networks capable of processing time-variant data. Each folder contains videos each with the following data: Endoscopic video as mp4 (*.mp4) Glottis segmentation as mask-file (hdf5 container, *.mask) Glottis segmentation as mp4 file (*_mask.mp4) Metadata as JSON file (*.meta) Glottal midline annotation as JSON file (*.points)

本研究为GlottisNetV2模型提供了时变训练与测试数据集。具体而言，本数据集依托于自动声门分割基准数据集（BAGLS dataset）。该数据集为三维数据（维度依次为时间、y轴、x轴），可用于支持可处理时变数据的深度神经网络相关实验。每个文件夹内包含多组视频数据，且每组视频数据均对应如下类型的文件：mp4格式的内窥镜视频（*.mp4）、以HDF5容器格式存储的声门分割掩码文件（*.mask）、mp4格式的声门分割掩码可视化视频（*_mask.mp4）、JSON格式的元数据文件（*.meta）以及JSON格式的声门中线标注文件（*.points）。