dotfiles
flax
Our great sponsors
dotfiles | flax | |
---|---|---|
3 | 9 | |
3 | 5,497 | |
- | 4.7% | |
0.0 | 9.6 | |
almost 3 years ago | 3 days ago | |
Vim Snippet | Python | |
- | 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.
dotfiles
- Weird artifact with rofi launcher
-
[D] Why is tensorflow so hated on and pytorch is the cool kids framework?
I mainly use vim as my editor and UltiSnips to manage my snippets. By typing specific keywords then expanding them with a single click, it inserts my pre-made snippet and put me in the right places to edit what needs to be edited (e.g. Network architecture, optimizer, epochs, …). I use the same approach for basically everything that includes highly repetitive code: plotting, LaTeX templates,… Here are my snippets.
- Command for setting keyboard layout in i3 config doesn't work.
flax
-
What is the JAX/Flax equivalent of torch.nn.Parameter?
https://github.com/google/flax/discussions/919 https://flax.readthedocs.io/en/latest/_modules/flax/linen/attention.html
-
Announcing flax 0.2 - A fully featured ECS
Just as an FYI, you might be competing against another big open source project with the same name https://github.com/google/flax
-
Flax: How to use one linen module inside another for training?
I have asked the same question on the Flax discussion page on Github as well.
-
[D] Should We Be Using JAX in 2022?
What's your favorite Deep Learning API for JAX - Flax, Haiku, Elegy, something else?
-
PyTorch vs. TensorFlow in 2022
As a researcher in RL & ML in a big industry lab, I would say most of my colleagues are moving to JAX 0https://github.com/google/jax], which this article kind of ignores. JAX is XLA-accelerated NumPy, it's cool beyond just machine learning, but only provides low-level linear algebra abstractions. However you can put something like Haiku [https://github.com/deepmind/dm-haiku] or Flax [https://github.com/google/flax] on top of it and get what the cool kids are using :)
- [D] Getting Started with Deep Learning in JAX with Treex in 16 lines
-
[D] JAX learning resources?
- https://github.com/google/flax/tree/main/examples
- Why would I want to develop yet another deep learning framework?
-
[D] Why is tensorflow so hated on and pytorch is the cool kids framework?
Any thoughts on Flax?
What are some alternatives?
tf-transformers - State of the art faster Transformer with Tensorflow 2.0 ( NLP, Computer Vision, Audio ).
dm-haiku - JAX-based neural network library
semver - Semantic Versioning Specification
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
trax - Trax — Deep Learning with Clear Code and Speed
equinox - Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
Flux.jl - Relax! Flux is the ML library that doesn't make you tensor
objax
jaxline
jax - Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
diffrax - Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/