# PaddleCFD **Repository Path**: paddlepaddle/PaddleCFD ## Basic Information - **Project Name**: PaddleCFD - **Description**: PaddleCFD is a deep learning toolkit for surrogate modeling, equation discovery, shape optimization and flow-control strategy discovery in the field of fluid mechanics. - **Primary Language**: Python - **License**: Apache-2.0 - **Default Branch**: develop - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 1 - **Forks**: 0 - **Created**: 2025-07-25 - **Last Updated**: 2025-08-16 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # PaddleCFD ## About PaddleCFD PaddleCFD is a deep learning toolkit for surrogate modeling, equation discovery, shape optimization and flow-control strategy discovery in the field of fluid mechanics. Currently, it mainly supports surrogate modeling, including models based on Fourier Neural Operator (FNO), Transformer, Diffusion Model (DM), Kolmogorov-Arnold Networks (KAN) and DeepONet. This is an image ## Code structure - `doc`: documentation - `examples`: example scripts - `ppcfd/data`: data-process source code - `ppcfd/model`: model source code - `ppcfd/utils`: utils code - `source`: source code of paddlepaddle custom operators ## How to run ### Installation ##### Image pulling & container running ```bash # Pull docker image docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddle:3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6 # Run docker container nvidia-docker run --name ppcfd-container -v /home/:/home --network=host -it --shm-size 64g ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddle:3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6 /bin/bash ``` ##### Conda environment installation ```bash # Clone PaddleCFD git clone https://github.com/PaddlePaddle/PaddleCFD.git cd PaddleCFD # Create conda environment conda create --name ppcfd python=3.10 conda activate ppcfd python -m pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/ # Download and install paddle-backended Open3D wget https://paddle-org.bj.bcebos.com/paddlecfd/envs/open3d-0.18.0+da239b25-cp310-cp310-manylinux_2_31_x86_64.whl python -m pip install open3d-0.18.0+da239b25-cp310-cp310-manylinux_2_31_x86_64.whl -i https://pypi.tuna.tsinghua.edu.cn/simple # Compile customed operator to conda environment wget -nc https://paddle-org.bj.bcebos.com/paddlescience/cmake-3.23.0-linux-x86_64.tar.gz tar -zxvf cmake-3.23.0-linux-x86_64.tar.gz rm -f cmake-3.23.0-linux-x86_64.tar.gz PATH=$PWD/cmake-3.23.0-linux-x86_64/bin:$PATH cd source/ppfno_op python -m pip install --no-build-isolation -v . ``` ##### PaddleCFD package installation (Choose one of the following) ```bash # Install PaddleCFD from sourcecode at PaddleCFD root directory python -m pip install -e . -i https://pypi.tuna.tsinghua.edu.cn/simple # Install PaddleCFD from pypi python -m pip install ppcfd -i https://pypi.tuna.tsinghua.edu.cn/simple ``` ### Quick start ```bash # Run examples cd PaddleCFD/examples/xxx/xxx run the example according to the example README.md ``` ## APIs [ppcfd/data](./doc/data.md) ## Community Join PaddleCFD WeChat group to discuss with us! This is an image ## License PaddleCFD is provided under the [Apache-2.0 license](./LICENSE)