Skip to main content

PaddleCFD is a deep learning toolkit for surrogate modeling, equation discovery, shape optimization and flow-control strategy discovery in the field of fluid mechanics.

Project description

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
# 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
# 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)
# 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

# Run examples
cd PaddleCFD/examples/xxx/xxx
run the example according to the example README.md

APIs

ppcfd/data

Community

Join PaddleCFD WeChat group to discuss with us!

This is an image

License

PaddleCFD is provided under the Apache-2.0 license

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ppcfd-0.3.0-py3-none-any.whl (234.3 kB view details)

Uploaded Python 3

File details

Details for the file ppcfd-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: ppcfd-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 234.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.18

File hashes

Hashes for ppcfd-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6dc7b904b69736202bdaac574a7ae804f21d679a1ab650256f77ae93617c56a5
MD5 e2d34a30cfb101b09e6a0cc1a6cced96
BLAKE2b-256 69a2546822aef748f9cfcfbb6262e154664c9323f413ea532a6c075ea852cc60

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page