Installation Deployment

MindSpore Flow Installation

Features

Solving PINNs Based on MindSpore Flow

Physics-driven

1D Burgers
2D stabilized Darcy Problem
2D Cylinder Flow
2D & 3D Poisson
Two-dimensional Taylor Green Vortex
Inverse Navier-Stokes Problem
Neural Representation Method for Boltzmann Equation
PINNs for Kovasznay Flow
Raynold-averaged Navier-Stokes
PINNs for Point Source Poisson

Data-driven

AI Industrial Flow Simulation Model (DongFang YuFeng)
FNO for 1D Burgers
FNO for 2D Navier-Stokes
KNO for 1D Burgers
KNO for 2D Navier-Stokes
Multi-timestep Complicated Flow Field Prediction with Transonic Airfoil under Data Driven Mode(with Two Kinds of Backbones: FNO2D and UNET2D)
Reduced order model for three-dimensional unsteady flow
FNO for 3D Navier-Stokes

Data Mechanism Fusion

PDE-Net for Convection-Diffusion Equation
PeRCNN for 2D burgers Equation
PeRCNN for 3D Reaction-Diffusion Equation

CFD-solver

1D Lax Tube
1D Sod Tube
2D Couette Flow
2D Riemann

API Reference

mindflow.cell
mindflow.cfd
mindflow.common
mindflow.data
mindflow.geometry
mindflow.loss
mindflow.operators
mindflow.pde

RELEASE NOTES

Release Notes

MindSpore

»
mindflow.operators
View page source

mindflow.operators

API Name	Description	Supported Platforms
`mindflow.operators.batched_hessian`
`mindflow.operators.batched_jacobian`

Previous Next

© Copyright MindSpore.

Built with Sphinx using a theme provided by Read the Docs.