Zygote.jl
abs_cd
Zygote.jl | abs_cd | |
---|---|---|
9 | 9 | |
1,439 | 70 | |
0.4% | - | |
8.1 | 7.8 | |
about 1 month ago | 3 months ago | |
Julia | Python | |
GNU General Public License v3.0 or later | GNU Affero General Public License v3.0 |
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.
Zygote.jl
-
Yann Lecun: ML would have advanced if other lang had been adopted versus Python
If you look at Julia open source projects you'll see that the projects tend to have a lot more contributors than the Python counterparts, even over smaller time periods. A package for defining statistical distributions has had 202 contributors (https://github.com/JuliaStats/Distributions.jl), etc. Julia Base even has had over 1,300 contributors (https://github.com/JuliaLang/julia) which is quite a lot for a core language, and that's mostly because the majority of the core is in Julia itself.
This is one of the things that was noted quite a bit at this SIAM CSE conference, that Julia development tends to have a lot more code reuse than other ecosystems like Python. For example, the various machine learning libraries like Flux.jl and Lux.jl share a lot of layer intrinsics in NNlib.jl (https://github.com/FluxML/NNlib.jl), the same GPU libraries (https://github.com/JuliaGPU/CUDA.jl), the same automatic differentiation library (https://github.com/FluxML/Zygote.jl), and of course the same JIT compiler (Julia itself). These two libraries are far enough apart that people say "Flux is to PyTorch as Lux is to JAX/flax", but while in the Python world those share almost 0 code or implementation, in the Julia world they share >90% of the core internals but have different higher levels APIs.
If one hasn't participated in this space it's a bit hard to fathom how much code reuse goes on and how that is influenced by the design of multiple dispatch. This is one of the reasons there is so much cohesion in the community since it doesn't matter if one person is an ecologist and the other is a financial engineer, you may both be contributing to the same library like Distances.jl just adding a distance function which is then used in thousands of places. With the Python ecosystem you tend to have a lot more "megapackages", PyTorch, SciPy, etc. where the barrier to entry is generally a lot higher (and sometimes requires handling the build systems, fun times). But in the Julia ecosystem you have a lot of core development happening in "small" but central libraries, like Distances.jl or Distributions.jl, which are simple enough for an undergrad to get productive in a week but is then used everywhere (Distributions.jl for example is used in every statistics package, and definitions of prior distributions for Turing.jl's probabilistic programming language, etc.).
-
How long till Julia could be the default language to learn ML?
I think julia has a lot going for it. I feel like autograd is one of the bigger ones given that it's a language feature basically (https://github.com/FluxML/Zygote.jl for reference). I think the ecosystem is a bit of an uphill battle though.
-
Neural networks with automatic differentiation.
Also check out https://github.com/FluxML/Zygote.jl which is the AD engine
-
PyTorch 1.8 release with AMD ROCm support
> There's sadly no performant autodiff system for general purpose Python.
Like there is for general purpose Julia? (https://github.com/FluxML/Zygote.jl)
-
The KimKlone Microcomputer
Thanks again. Like you said it is fun to dream (ask the "Scheme Machine" guys sometime about how they would go about it now), but practically with technology like Julia's Zygote:
https://github.com/FluxML/Zygote.jl
the efficiency of autodiff might be similar to that of an opcode anyway.
So, how did DEC do on the Alpha processor? I always heard good things about it--IIRC it was based on the VAX, but 64 bit. I learned PDP-11 assembler at RPI, during their college program for high school students in about 1984. We hand assembled code and really got to know the architecture.
- FluxML/Zygote.jl -- v0.6.3 should implement a `jacobian` function but doesn't?
-
Did the makers of Zygote.jl use category theory to define their approach to computable autodiff?
and make that computable. It seems like line 88 --> 90 of this file in Zygote does that: https://github.com/FluxML/Zygote.jl/blob/master/src/compiler/chainrules.jl
- Study group: Structure and Interpretation of Classical Mechanics in Clojure
-
Ask HN: Show me your Half Baked project
It's super powerful
For example Zygote.jl (https://github.com/FluxML/Zygote.jl) implements reverse mode automatic differentiation, by defining a function that is a generated transformation of the function being differentiated.
abs_cd
-
Looking for co-maintainers (AUR)
Get a CI to check if pkg build in clean environments. So many users will falsely report broken packages while they simply ran makepkg in their arch installation & the build system pulls crap from it into the build process & it fails despite your pkg being fine. It's a shame every AUR helper except aurutils still doesn't support building in clean chroots, but you can't change that. I build https://github.com/bionade24/abs_cd for that, which end the end served a custom repo easing the installation for users, too. There are plenty alternatives to my SW out there, too.
-
ROS OS support be like
You can find the CD status on https://abs-cd.oscloud.info/
-
ABS-CD, a CI/CD for Arch packages, now features automatic check for changes in the PKGBUILD repo.
This commit should also be a good example on how to configure crond to work well with logging in an Arch container.
-
Ask HN: Show me your Half Baked project
https://github.com/bionade24/abs_cd
A CI/CD with webinterface for Archlinux packages which optional AUR push support if builds succeed. It's based on Django and works with Docker/Podman. I originally made it for my own AUR packages (> 300), I needed accessible build logs if I want to collab, which the common builders didn't provide. I made the project public and it's crazy for me as an open source beginner to see how many people like this. The basic features are complete, but things like multiarch are getting add soon.
-
Show HN: A CI/CD for Archlinux packages with optional AUR push
It now has podman compatibility as as a PR: https://github.com/bionade24/abs_cd/pull/8
-
ABS_CD - a CI/CD for Archlinux packages with optional AUR push support making it easy to serve a private repo.
It now should have podman compatibility, would be nice if you test it: https://github.com/bionade24/abs_cd/pull/8
-
Can I automatically put in my password after building with yay
If it really takes that long (and you maybe have more than one device or your friends use the same packages) and you can't find a user already packaging it in their private repo you could host an own repo in you local network. I created a CI/CD software for Arch packages which makes this easier: https://github.com/bionade24/abs_cd
What are some alternatives?
Enzyme - High-performance automatic differentiation of LLVM and MLIR.
DIY-arcade - How to build your own full-size arcade machine from scratch
ForwardDiff.jl - Forward Mode Automatic Differentiation for Julia
tinyjam - A radically simple, zero-configuration static site generator in JavaScript
Tullio.jl - ⅀
smug - Session manager and task runner for tmux. Start your development environment within one command.
TensorFlow.jl - A Julia wrapper for TensorFlow
json-tail
Flux.jl - Relax! Flux is the ML library that doesn't make you tensor
stdnum-js - A JavaScript library to provide functions to handle, parse and validate standard numbers.
InvertibleNetworks.jl - A Julia framework for invertible neural networks
wcp