five

Unified Graph Neural Network Force-field for the Periodic Table for Solids

收藏
DataCite Commons2022-12-12 更新2024-07-29 收录
下载链接:
https://figshare.com/articles/dataset/Unified_Graph_Neural_Network_Force-field_for_the_Periodic_Table_for_Solids/21667874/1
下载链接
链接失效反馈
官方服务:
资源简介:
GitHub-repo: https://github.com/usnistgov/alignn <br> Dataset, model training config file and model for ALIGNN-FF: <br> To train the model: <br> train_folder_ff.py --root_dir "PATH" --config "config.json" --output_dir="temp" <br> Here, train_folder_ff.py is a global executable that comes with ALIGNN installation. PATH is the folder path where you kept the id_prop.json file after untarring it (tar -xvzf id_prop.json.tgz). config.json is the configuration file provided here. <br> Note that the energy data is energy/per atom in eV and forces on atoms are in eV/Angstrom. <br> To use the model: <br> <pre><code>run_alignn_ff.py --file_path alignn/examples/sample_data/POSCAR-JVASP-10.vasp --task="unrelaxed_energy"</code></pre> <pre><code><br></code></pre> <pre><code><br></code></pre>
提供机构:
figshare
创建时间:
2022-12-02
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作