SimXRD-4M

• GitHub : https://github.com/Bin-Cao/SimXRD

Introduction

The SimXRD database is a comprehensive resource for spectral data analysis, designed to facilitate the identification of crystal materials both in and out library.

Version V1.0.0 (May 2024)

This version introduces datasets for both In Library (IL) and Out Library (OL) identification.

In Library (IL) Identification

• Train Dataset (Part One): ILtrainV1_P1 DOI:10.57967/hf/2878
• Train Dataset (Part Two): ILtrainV1_P2 DOI:10.57967/hf/2879
• Validation Dataset: ILvalV1 DOI:10.57967/hf/2880
• Test Dataset: ILtestV1 DOI:10.57967/hf/2881

Crystal Data

If you need the organized crystal database, visit here: https://huggingface.co/datasets/caobin/CrystDB

Out Library (OL) Identification

• Train Dataset: OLtrainV1 DOI:10.57967/hf/2877
• Validation Dataset: OLvalV1 DOI:10.57967/hf/2876
• Test Dataset: OLtestV1 DOI:10.57967/hf/2875

Check Dataset

To check the dataset, you can use the following command:

pip install ase

ase db {name}.db

Notes:

• Ensure you replace {name} with the appropriate dataset name when using the ase db command.