UA - Gaussian Depth Disc (GDD dataset)

Dear reader,

Welcome! You must be an avid profilometry person to be interested in downloading our dataset.

Before you start tinkering with the dataset package please do install the requirements.txt libraries for a more easy step into operating this system.

We hope to have made the hierarchy of the package as clear as possible! Also note that this system was written in VScode.

Find your way to the examples folder, there you can find "entire_dataset". This folder contains a script to divide the original h5 file containing all data

into whatever sub-options you'd like. An example divided dataset has already been given namely the 80/20 division of respectively training and validation

data in the "example_dataset" folder.

In the folder models you will find the two models mentioned in the publication related to this dataset. These two were published with the dataset since they

had either the highest performance on the training and validation dataset (DenseNet) or on the random physical object test (UNet).

A training script is included (training_script.py) to show you how these models were created, so if you wish to add new models to the networks.py file in the classes folder, you can!

The validation jupyter notebook contains two visualisation tools to quickly and neatly show the performance of your model on the recorded dataset.

Lastly to test on the recorded object you can run the "test_physical_data.py" script.

We hope this helps you in your research and we hope it further improves any and all research within the single shot profilometry field! 😊

Kind regards,

Rhys Evans,

InViLab,

University of Antwerp, Belgium

尊敬的使用者：

欢迎使用本数据集！想必您已是轮廓测量术（profilometry）领域的资深研究者，才会关注本数据集的下载。

在您开始操作本数据集套件前，请务必先安装requirements.txt文件中列出的依赖库，以简化后续系统运行流程。

我们已尽可能明晰本套件的目录层级结构。此外请注意，本系统基于VScode编写。

请进入examples文件夹，其中包含"entire_dataset"目录。该目录内附带脚本，可将存储全部数据的原始HDF5格式文件按您的需求划分为任意子数据集。此外，"example_dataset"目录中已提供一个划分示例：将数据集按80:20的比例分别划分为训练集与验证集。

在"models"文件夹中，您可找到本数据集配套学术论文中提及的两款模型。这两款模型随本数据集一同发布，分别为在训练与验证集上取得最优性能的密集卷积网络（DenseNet），以及在随机实物测试中表现最佳的U型网络（UNet）。

本套件附带训练脚本training_script.py，用于演示这两款模型的构建流程。若您希望向classes文件夹下的networks.py文件中添加新模型，亦可自行实现。

验证用Jupyter Notebook内置两款可视化工具，可快速且清晰地展示您的模型在本数据集上的性能表现。

最后，若需在实物测试数据上开展验证，您可运行"test_physical_data.py"脚本。

衷心祝愿本数据集能为您的研究提供助力，并推动单次成像轮廓测量术（single-shot profilometry）领域的相关研究发展😊

致以诚挚问候：
里斯·埃文斯（Rhys Evans）
因维实验室（InViLab）
安特卫普大学，比利时