ivy
PDEBench
ivy  PDEBench  

1  2  
10,475  693  
  4.5%  
10.0  6.3  
over 1 year ago  3 months ago  
Python  Python  
GNU General Public License v3.0 or later  GNU General Public License v3.0 or later 
Stars  the number of stars that a project has on GitHub. Growth  month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ivy

Need internship/part time role in AI/ML/Data Science field.
As a volunteer developer at Ivy, I also been actively contributing to the project for several months now. I extended the Ivy Functional API by adding some linear algebra functions  matrix_exp (https://github.com/ivydl/ivy/blob/dev/ivy/linalg/matrix_exp.py) and diff (https://github.com/ivydl/ivy/blob/dev/ivy/linalg/diff.py)  to all four popular deep learning frameworks: NumPy, TensorFlow, PyTorch, and JAX. These functions allowed developers to perform matrix exponentiation and differentiation operations more efficiently and easily using any of these frameworks.
PDEBench

[P] LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite
LagrangeBench is a machine learning benchmarking library for CFD particle problems based on JAX. It is designed to evaluate and develop learned particle models (e.g. graph neural networks) on challenging physical problems. To our knowledge it's the first benchmark for this specific set of problems. Our work was inspired by the gridbased benchmarks of PDEBench and PDEArena, and we propose it as a Lagrangian alternative.

[D] what are the SOTA neural PDE solvers besides FNO?
try https://github.com/pdebench/pdebench
What are some alternatives?
machine_learning_refined  Notes, examples, and Python demos for the 2nd edition of the textbook "Machine Learning Refined" (published by Cambridge University Press).
squirrelcore  A Python library that enables ML teams to share, load, and transform data in a collaborative, flexible, and efficient way :chestnut:
pennylane  PennyLane is a crossplatform Python library for quantum computing, quantum machine learning, and quantum chemistry. Train a quantum computer the same way as a neural network.
pdearena
tensorsensor  The goal of this library is to generate more helpful exception messages for matrix algebra expressions for numpy, pytorch, jax, tensorflow, keras, fastai.
transformers  ðŸ¤— Transformers: Stateoftheart Machine Learning for Pytorch, TensorFlow, and JAX.
tensorboardX  tensorboard for pytorch (and chainer, mxnet, numpy, ...)
d2len  Interactive deep learning book with multiframework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
leptonai  A Pythonic framework to simplify AI service building
ivy  Convert Machine Learning Code Between Frameworks
foolbox  A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
thinc  ðŸ”® A refreshing functional take on deep learning, compatible with your favorite libraries