https://github.com/taichi-dev/difftaichi

10 differentiable physical simulators built with Taichi differentiable programming (DiffTaichi, ICLR 2020)
https://github.com/taichi-dev/difftaichi

differentiable-programming gpu graphics robotics simulation taichi

Last synced: 18 days ago
JSON representation

10 differentiable physical simulators built with Taichi differentiable programming (DiffTaichi, ICLR 2020)

• Host: GitHub
• URL: https://github.com/taichi-dev/difftaichi
• Owner: taichi-dev
• Created: 2019-12-03T04:35:44.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2023-11-01T09:01:54.000Z (about 1 year ago)
• Last Synced: 2024-10-16T07:05:35.992Z (2 months ago)
• Topics: differentiable-programming, gpu, graphics, robotics, simulation, taichi
• Homepage:
• Size: 345 KB
• Stars: 2,465
• Watchers: 64
• Forks: 259
• Open Issues: 16
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-taichi - DiffTaichi - Differentiable Programming for Physical Simulation. (Applications / **Machine Learning**)
• awesome-taichi - DiffTaichi - Differentiable Programming for Physical Simulation. (**Machine Learning**)

README

        


  
 python3 diffmpm.py 

  

        


# DiffTaichi: Differentiable Programming for Physical Simulation (ICLR 2020)

*Yuanming Hu, Luke Anderson, Tzu-Mao Li, Qi Sun, Nathan Carr, Jonathan Ragan-Kelley, Frédo Durand*

[[Paper]](https://arxiv.org/abs/1910.00935) [[Video] (with instructions to reproduce every demo)](https://www.youtube.com/watch?v=Z1xvAZve9aE)

### Differentiable programming in Taichi allows you to optimize neural network controllers efficiently with brute-force gradient descent, instead of using reinforcement learning.

The *DiffTaichi* differentiable programming framework is now officially part of [Taichi](https://github.com/yuanming-hu/taichi). This repo only contains examples.

DiffTaichi significantly boosts the performance and productivity of differentiable physical simulators. For example, the differentiable elastic object simulator (ChainQueen) in DiffTaichi is 188x faster than an implementation in TensorFlow. The DiffTaichi version also runs as fast as the CUDA implementation, with the code being 4.2x shorter.

Most of the 10 differentiable simulators can be implemented **within 2-3 hours**.

Questions regarding the simulators/autodiff compiler go to Yuanming Hu (yuanming __at__ mit.edu) or [Issues](https://github.com/yuanming-hu/difftaichi/issues).

### Note: Updates on October 27 2021

Examples are now compatible with Taichi `v0.8.3`. Please update Taichi if you are using an old version.

## How to run

Step 1: Install [`Taichi`](https://github.com/taichi-dev/taichi) with `pip`:

(Most examples do **not** need a GPU to run.)

```bash

python3 -m pip install taichi

```

Step 2: Run example scripts in the `examples` folder: (Please wait for all GIFs to load :-)

### Differentiable Elastic Object Simulator [`python3 diffmpm.py`]

Gradient descent iteration 0 and gradient descent iteration 80: 

 

### Differentiable 3D Elastic Object Simulator [`python3 diffmpm3d.py`]

Gradient descent iteration 40: 



### Differentiable 3D Fluid Simulator [`python3 liquid.py`]

Gradient descent iteration 450: 



### Differentiable Height Field Water Simulator [`python3 wave.py`]

Gradient descent iteration 180:



### Differentiable (Adversarial) Water Renderer [`python3 water_renderer.py`]

Differentiable water simulation + differentiable water rendering + (differentiable) CNN

**Optimization goal:** find an initial water height field, so that after simulation and shading, VGG16 thinks the squirrel image is a goldfish. Input image: VGG16=fox squirrel (42.21%)



**Left:** center activation .  **Right:** An activation that fools VGG (VGG16=goldfish (99.91%))



### Differentiable Rigid Body Simulator [`python3 rigid_body.py [1/2] train`]

2048 time steps. Gardient descent iteration 20: 

 

### Differentiable Mass-Spring Simulator [`python3 mass_spring.py [1/2/3] train`]

682 time steps.

Gardient descent iteration 20: 

     

### Differentiable Billiard Simulator [`python3 billiards.py`]

Gardient descent iteration 0 and gradient descent iteration 100: 

 

See the video for the remaining two simulators.

## Bibtex

```

@article{hu2019difftaichi,

  title={DiffTaichi: Differentiable Programming for Physical Simulation},

  author={Hu, Yuanming and Anderson, Luke and Li, Tzu-Mao and Sun, Qi and Carr, Nathan and Ragan-Kelley, Jonathan and Durand, Fr{\'e}do},

  journal={ICLR},

  year={2020}

}

@article{hu2019taichi,

  title={Taichi: a language for high-performance computation on spatially sparse data structures},

  author={Hu, Yuanming and Li, Tzu-Mao and Anderson, Luke and Ragan-Kelley, Jonathan and Durand, Fr{\'e}do},

  journal={ACM Transactions on Graphics (TOG)},

  volume={38},

  number={6},

  pages={201},

  year={2019},

  publisher={ACM}

}

```