PaddleMaterials

🚀 Introduction

PaddleMaterials is an end-to-end AI4Materials toolkit built on the PaddlePaddle deep learning framework. Designed as a data-mechanism dual-driven platform for developing and deploying foundation models in materials science, PPMat enables researchers to efficiently build AI models and accelerate material discovery using pretrained models.

🧩 Core Capabilities

🧱 Supported Materials

• Inorganic Crystals - Well-supported with multiple datasets and pretrained models
• Organic Molecules - Support for multiple datasets and pretrained models including small molecules and partial polymers

✨ Why PaddleMaterials?

• ✅ Rich Pretrained Models & AI-ready Datasets - 50+ pretrained models ready for inference and Multiple curated datasets for training
• ✅ Multi-Task Integration - Unified framework across tasks of PP, SG, MLIP, ES, SE, SPEN etc.
• ✅ Multi-Hardware Support - Full support for NVIDIA GPUs and MetaX GPUs and Intel CPUs
• ✅ Production-Ready - Easy to use with standandlize design & distributed training, mixed precision, checkpoint recovery

📑 Support Tasks

🤖 Available Pretrained Models

Full model list: See MODEL_REGISTRY

🚀 Get Started

🔧 Installation

Please refer to the installation document for your hardware environment. See SupportedHardwareList for more multi-hardware adaptation information.

⚡ Easy Inference

Property Prediction

Predict material formation energy using a pretrained MEGNet model:

python property_prediction/predict.py \
    --model_name='megnet_mp2018_train_60k_e_form' \
    --weights_name='best.pdparams' \
    --input_format=cif --input_path='./property_prediction/example_data/cifs/' \
    --output_path='results/'

Structure Generation

Generate novel crystal structures using a pretrained MatterGen model:

python structure_generation/sample.py \
    --model_name='mattergen_mp20' \
    --weights_name='latest.pdparams' \
    --output_path='result_mattergen_mp20/' \
    --mode='by_num_atoms' \
    --num_atoms=4

Interatomic Potentials

Predict energy and forces using a pretrained MatterSim model:

python interatomic_potentials/predict.py \
    --model_name='mattersim_1M' \
    --weights_name='mattersim-v1.0.0-1M_model.pdparams' \
    --input_format=cif --input_path='./interatomic_potentials/example_data/cifs/' \
    --output_path='results/'

Electronic Structure

Predict electron density from the bundled methane example using a pretrained InfGCN model:

python electronic_structure/predict.py \
    --model_name='infgcn_qm9' \
    --weights_name='best.pdparams' \
    --input_format=mol --input_path='electronic_structure/example_data/methane.mol' \
    --grid_shape=8 \
    --grid_batch_size=4096 \
    --output_path='output/infgcn_qm9/methane'

See the InfGCN prediction guide for dataset-based and local-checkpoint inference.

Spectrum Elucidation

Run NMR spectrum elucidation using the bundled example and a pretrained DiffNMR model:

python spectrum_elucidation/sample.py \
    --model_name='diffnmr_msdnmr_nless15' \
    --weights_name='best.pdparams' \
    --output_path='result_diffnmr_nless15/'

Spectrum Enhancement

Enhance STEM images using a pretrained SFIN model:

python spectrum_enhancement/predict.py \
    --model_name='sfin_haadf_enhance' \
    --weights_name='best.pdparams' \
    --input_path='path/to/noisy_image.png' \
    --output_path='result_sfin/'

🏋️ Start Training

For training and fine-tuning, refer to the documentation.

🤝 Contributors & Cooperation & Community

Thanks to all contributors who have helped build PaddleMaterials！

Thanks for the following organiziton for cooprative support!

Join the PaddleMaterials WeChat group to discuss with us!

🛠️ Contribute to PaddleMaterials

For developer, please refer to architecture.

📜 License

PaddleMaterials is licensed under the Apache License 2.0.

🎓 Citation

@misc{paddlematerials2025,
  title={PaddleMaterials, a deep learning toolkit based on PaddlePaddle for material science.},
  author={PaddleMaterials Contributors},
  howpublished = {\url{https://github.com/PaddlePaddle/PaddleMaterials}},
  year={2025}
}

🙏 Acknowledgements

This repository references code from the following projects:

PaddleScience | Matgl | CDVAE | DiffCSP | MatterGen | MatterSim | CHGNet | AIRS