Leibniz is a python package which provide facilities to express learnable partial differential equations with PyTorch

Last update: Aug 07, 2022

Overview

Leibniz

Leibniz is a python package which provide facilities to express learnable differential equations with PyTorch

We also provide UNet, ResUNet and their variations, especially the Hyperbolic blocks for ResUNet.

Install

pip install leibniz

How to use

Physics-informed

As an example we solve a very simple advection problem, a box-shaped material transported by a constant steady wind.

import torch as th
import leibniz as lbnz

from leibniz.core3d.gridsys.regular3 import RegularGrid
from leibniz.diffeq import odeint as odeint


def binary(tensor):
    return th.where(tensor > lbnz.zero, lbnz.one, lbnz.zero)

# setup grid system
lbnz.bind(RegularGrid(
    basis='x,y,z',
    W=51, L=151, H=51,
    east=16.0, west=1.0,
    north=6.0, south=1.0,
    upper=6.0, lower=1.0
))
lbnz.use('x,y,z') # use xyz coordinate

# giving a material field as a box 
fld = binary((lbnz.x - 8) * (9 - lbnz.x)) * \
      binary((lbnz.y - 3) * (4 - lbnz.y)) * \
      binary((lbnz.z - 3) * (4 - lbnz.z))

# construct a constant steady wind
wind = lbnz.one, lbnz.zero, lbnz.zero

# transport value by wind
def derivitive(t, clouds):
    return - lbnz.upwind(wind, clouds)

# integrate the system with rk4
pred = odeint(derivitive, fld, th.arange(0, 7, 1 / 100), method='rk4')

UNet, ResUNet and variations

from leibniz.unet import UNet
from leibniz.nn.layer.hyperbolic import HyperBottleneck
from leibniz.nn.activation import CappingRelu

unet = UNet(6, 1, normalizor='batch', spatial=(32, 64), layers=5, ratio=-1,
            vblks=[4, 4, 4, 4, 4], hblks=[1, 1, 1, 1, 1],
            scales=[-1, -1, -1, -1, -1], factors=[1, 1, 1, 1, 1],
            block=HyperBottleneck, relu=CappingRelu(), final_normalized=False)

We provide a ResUNet implementation, which is a UNet variation can insert ResNet blocks between layers. The supported ResNet blocks are include

Pure ResNet: Basic, Bottleneck block
SENet variations: Basic, Bottleneck block
Hyperbolic variations: Basic, Bottleneck block

We support 1d, 2d, 3d UNet.

normalizor are include:

batch: BatchNorm
layer: LayerNorm
instance: InstanceNorm

Other hyperparameters are include:

spatial: the sizes of the spatial dimentions
ratio: the ratio to decide the intial number of channels into the UNet
vblks: how many vertical blocks is inserted between two layers
hblks: how many horizontal blocks is inserted in the skip connections
scales: scale factors(power-2-based) on the spatial dimentions
factors: expand or shrink factors(power-2-based) on the channels
final_normalized: wheather to scale to final result between 0 to 1

Piecewise Linear normalizor

Piecewise Linear normalizor provide an learnable monotonic peicewise linear functions and its inverse fucntion. The API is shown as below

from leibniz.nn.normalizor import PWLNormalizor

# on 3 channels, given 128 segmented pieces, and assuming the input data have a zero mean and 1.0 std
pwln = PWLNormalizor(3, 128, mean=0.0, std=1.0)

normed = pwln(input)
output = pwln.inverse(normed)

How to release

python3 setup.py sdist bdist_wheel
python3 -m twine upload dist/*

git tag va.b.c master
git push origin va.b.c

Contributors

Mingli Yuan (Mountain)
Xiang Pan (Panpanx)
Yi Liu (YiLiu)

Acknowledge

We included source code with minor changes from torchdiffeq by Ricky Chen, because of two purpose:

package torchdiffeq is not indexed by pypi
package torchdiffeq is very convenient and mandatory

All our contribution is based on Ricky's Neural ODE paper (NIPS 2018) and his package.

Releases(v0.1.42)

v0.1.42(Aug 14, 2021)

try other formula in hyperbolic blocks
Source code(tar.gz)
Source code(zip)
v0.1.41(Aug 13, 2021)

Leibniz is a python package which provide facilities to express learnable differential equations with PyTorch. We also provide UNet, ResUNet and their variations, especially the Hyperbolic blocks for ResUNet.
Source code(tar.gz)
Source code(zip)

Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechanism for Generalized Face Presentation Attack Detection

LMFD-PAD Note This is the official repository of the paper: LMFD-PAD: Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechani

28 Dec 2, 2022

A Planar RGB-D SLAM which utilizes Manhattan World structure to provide optimal camera pose trajectory while also providing a sparse reconstruction containing points, lines and planes, and a dense surfel-based reconstruction.

ManhattanSLAM Authors: Raza Yunus, Yanyan Li and Federico Tombari ManhattanSLAM is a real-time SLAM library for RGB-D cameras that computes the camera

117 Dec 28, 2022

Implementation of "Scaled-YOLOv4: Scaling Cross Stage Partial Network" using PyTorch framwork.

YOLOv4-large This is the implementation of "Scaled-YOLOv4: Scaling Cross Stage Partial Network" using PyTorch framwork. YOLOv4-CSP YOLOv4-tiny YOLOv4-

2k Jan 2, 2023

Unofficial pytorch implementation of 'Image Inpainting for Irregular Holes Using Partial Convolutions'

pytorch-inpainting-with-partial-conv Official implementation is released by the authors. Note that this is an ongoing re-implementation and I cannot f

525 Jan 1, 2023

Reproduce partial features of DeePMD-kit using PyTorch.

DeePMD-kit on PyTorch For better understand DeePMD-kit, we implement its partial features using PyTorch and expose interface consuing descriptors. Tec

8 Dec 17, 2022

A PyTorch implementation of ICLR 2022 Oral paper PiCO: Contrastive Label Disambiguation for Partial Label Learning

PiCO: Contrastive Label Disambiguation for Partial Label Learning This is a PyTorch implementation of ICLR 2022 Oral paper PiCO; also see our Project

83 May 11, 2022

A Python framework for developing parallelized Computational Fluid Dynamics software to solve the hyperbolic 2D Euler equations on distributed, multi-block structured grids.

pyHype: Computational Fluid Dynamics in Python pyHype is a Python framework for developing parallelized Computational Fluid Dynamics software to solve

21 Nov 22, 2022

Using NumPy to solve the equations of fluid mechanics together with Finite Differences, explicit time stepping and Chorin's Projection methods

Computational Fluid Dynamics in Python Using NumPy to solve the equations of fluid mechanics 🌊 🌊 🌊 together with Finite Differences, explicit time

4 Nov 12, 2022

Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, Ant Colony Optimization Algorithm,Immune Algorithm, Artificial Fish Swarm Algorithm, Differential Evolution and TSP(Traveling salesman)

scikit-opt Swarm Intelligence in Python (Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, Ant Colony Algorithm, Immune Algorithm,A

3.7k Jan 3, 2023

Leibniz is a python package which provide facilities to express learnable partial differential equations with PyTorch

Related tags

Overview

Leibniz

Install

How to use

Physics-informed

UNet, ResUNet and variations

Piecewise Linear normalizor

How to release

Contributors

Acknowledge

You might also like...

Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechanism for Generalized Face Presentation Attack Detection

A Planar RGB-D SLAM which utilizes Manhattan World structure to provide optimal camera pose trajectory while also providing a sparse reconstruction containing points, lines and planes, and a dense surfel-based reconstruction.

Implementation of "Scaled-YOLOv4: Scaling Cross Stage Partial Network" using PyTorch framwork.

Unofficial pytorch implementation of 'Image Inpainting for Irregular Holes Using Partial Convolutions'

Reproduce partial features of DeePMD-kit using PyTorch.

A PyTorch implementation of ICLR 2022 Oral paper PiCO: Contrastive Label Disambiguation for Partial Label Learning

A Python framework for developing parallelized Computational Fluid Dynamics software to solve the hyperbolic 2D Euler equations on distributed, multi-block structured grids.

Using NumPy to solve the equations of fluid mechanics together with Finite Differences, explicit time stepping and Chorin's Projection methods

Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, Ant Colony Optimization Algorithm,Immune Algorithm, Artificial Fish Swarm Algorithm, Differential Evolution and TSP(Traveling salesman)

Releases(v0.1.42)

v0.1.42(Aug 14, 2021)

v0.1.41(Aug 13, 2021)

Owner

Beijing ColorfulClouds Technology Co.,Ltd.

[NeurIPS 2019] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

Reproducible research and reusable acyclic workflows in Python. Execute code on HPC systems as if you executed them on your personal computer!

Create Own QR code with Python

Python/Rust implementations and notes from Proofs Arguments and Zero Knowledge

Optimizing DR with hard negatives and achieving SOTA first-stage retrieval performance on TREC DL Track (SIGIR 2021 Full Paper).

Some bravo or inspiring research works on the topic of curriculum learning.

A tool for making map images from OpenTTD save games

FaceAnon - Anonymize people in images and videos using yolov5-crowdhuman

PlaidML is a framework for making deep learning work everywhere.

Boostcamp AI Tech 3rd / Basic Paper reading w.r.t Embedding

Generating Anime Images by Implementing Deep Convolutional Generative Adversarial Networks paper

PyTorch implementation of federated learning framework based on the acceleration of global momentum

Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning

Deep Learning with PyTorch made easy 🚀 !

This repository is the offical Pytorch implementation of ContextPose: Context Modeling in 3D Human Pose Estimation: A Unified Perspective (CVPR 2021).

Adversarial Color Enhancement: Generating Unrestricted Adversarial Images by Optimizing a Color Filter

3D position tracking for soccer players with multi-camera videos

Conservative Q Learning for Offline Reinforcement Reinforcement Learning in JAX

RealTime Emotion Recognizer for Machine Learning Study Jam's demo

The LaTeX and Python code for generating the paper, experiments' results and visualizations reported in each paper is available (whenever possible) in the paper's directory