PDEBench
thinc
PDEBench | thinc | |
---|---|---|
2 | 4 | |
623 | 2,794 | |
3.7% | 0.5% | |
6.5 | 7.6 | |
about 1 month ago | 4 days ago | |
Python | Python | |
GNU General Public License v3.0 or later | MIT License |
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.
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 grid-based 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
thinc
-
JAX – NumPy on the CPU, GPU, and TPU, with great automatic differentiation
Agree, though I wouldn’t call PyTorch a drop-in for NumPy either. CuPy is the drop-in. Excepting some corner cases, you can use the same code for both. Thinc’s ops work with both NumPy and CuPy:
https://github.com/explosion/thinc/blob/master/thinc/backend...
-
Tinygrad: A simple and powerful neural network framework
I love those tiny DNN frameworks, some examples that I studied in the past (I still use PyTorch for work related projects) :
thinc.by the creators of spaCy https://github.com/explosion/thinc
-
good examples of functional-like python code that one can study?
thinc - defining neural nets in functional way jax, a new deep learning framework puts emphasis on functions rather than tensors, I've tested it for a couple of applications and it's really cool, you can write stuff like you'd write math expressions in papers using numpy. That speeds up development significantly, and makes code much more readable
- thinc - A refreshing functional take on deep learning, compatible with your favorite libraries
What are some alternatives?
squirrel-core - A Python library that enables ML teams to share, load, and transform data in a collaborative, flexible, and efficient way :chestnut:
quantulum3 - Library for unit extraction - fork of quantulum for python3
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
jax - Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
ivy - The Unified Machine Learning Framework [Moved to: https://github.com/unifyai/ivy]
horovod - Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
pdearena
extending-jax - Extending JAX with custom C++ and CUDA code
d2l-en - Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
dm-haiku - JAX-based neural network library
best-of-ml-python - 🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
AIF360 - A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.