jax-models
diffrax
jax-models | diffrax | |
---|---|---|
6 | 21 | |
138 | 1,256 | |
- | - | |
0.0 | 8.2 | |
almost 2 years ago | 6 days ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
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.
jax-models
-
[D] How to contribute to open source ML and DL without having access to high quality setup?
I was in the same position as you are and the best thing you can do is to start reproducing papers (that's what I did with jax-models). This will
-
[D] Should We Be Using JAX in 2022?
I've been using JAX, especially Flax for quite some time now for my reproducibility initiative (jax_models) and this is what I really appreciate about the framework
- Weekly updated open sourced model implementations in Flax
- Weekly updated open sourced deep learning model implementations in Flax
- [P] Weekly updated open sourced model implementations in Flax
diffrax
- Ask HN: What side projects landed you a job?
-
[P] Optimistix, nonlinear optimisation in JAX+Equinox!
Optimistix has high-level APIs for minimisation, least-squares, root-finding, and fixed-point iteration and was written to take care of these kinds of subroutines in Diffrax.
-
Show HN: Optimistix: Nonlinear Optimisation in Jax+Equinox
Diffrax (https://github.com/patrick-kidger/diffrax).
Here is the GitHub: https://github.com/patrick-kidger/optimistix
The elevator pitch is Optimistix is really fast, especially to compile. It
-
Scientific computing in JAX
Sure. So I've got some PyTorch benchmarks here. The main take-away so far has been that for a neural ODE, the backward pass takes about 50% longer in PyTorch, and the forward (inference) pass takes an incredible 100x longer.
-
[D] JAX vs PyTorch in 2023
FWIW this worked for me. :D My full-time job is now writing JAX libraries at Google. Equinox for neural networks, Diffrax for differential equation solvers, etc.
-
Returning to snake's nest after a long journey, any major advances in python for science ?
It's relatively early days yet, but JAX is in the process of developing its nascent scientific computing / scientific machine learning ecosystem. Mostly because of its strong autodifferentiation capabilities, excellent JIT compiler etc. (E.g. to show off one of my own projects, Diffrax is the library of diffeq solvers for JAX.)
-
What's the best thing/library you learned this year ?
Diffrax - solving ODEs with Jax and computing it's derivatives automatically functools - love partial and lru_cache fastprogress - simpler progress bar than tqdm
-
PyTorch 2.0
At least prior to this announcement: JAX was much faster than PyTorch for differentiable physics. (Better JIT compiler; reduced Python-level overhead.)
E.g for numerical ODE simulation, I've found that Diffrax (https://github.com/patrick-kidger/diffrax) is ~100 times faster than torchdiffeq on the forward pass. The backward pass is much closer, and for this Diffrax is about 1.5 times faster.
It remains to be seen how PyTorch 2.0 will compare, or course!
Right now my job is actually building out the scientific computing ecosystem in JAX, so feel free to ping me with any other questions.
-
Python 3.11 is much faster than 3.8
https://github.com/patrick-kidger/diffrax
Which are neural network and differential equation libraries for JAX.
[Obligatory I-am-googler-my-opinions-do-not-represent- your-employer...]
-
Ask HN: What's your favorite programmer niche?
Autodifferentiable programming!
Neural networks are the famous example of this, of course -- but this can be extended to all of scientific computing. ODE/SDE solvers, root-finding algorithms, LQP, molecular dynamics, ...
These days I'm doing all my work in JAX. (E.g. see Equinox or Diffrax: https://github.com/patrick-kidger/equinox, https://github.com/patrick-kidger/diffrax). A lot of modern work is now based around hybridising such techniques with neural networks.
I'd really encourage anyone interested to learn how JAX works under-the-hood as well. (Look up "autodidax") Lots of clever/novel ideas in its design.
What are some alternatives?
datasets - TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
deepxde - A library for scientific machine learning and physics-informed learning
flax - Flax is a neural network library for JAX that is designed for flexibility.
tiny-cuda-nn - Lightning fast C++/CUDA neural network framework
flaxmodels - Pretrained deep learning models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet, etc.
equinox - Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
juliaup - Julia installer and version multiplexer
GradCache - Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint
elegy - A High Level API for Deep Learning in JAX
dm-haiku - JAX-based neural network library