Zygote.jl
AI-basketball-analysis
Zygote.jl | AI-basketball-analysis | |
---|---|---|
9 | 12 | |
1,439 | 923 | |
0.4% | - | |
8.1 | 0.0 | |
about 1 month ago | about 1 year ago | |
Julia | 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.
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.
AI-basketball-analysis
-
[P] Basketball Shots Detection and Shooting Pose Analysis (Open Source)
Source code: https://github.com/chonyy/AI-basketball-analysis
- Show HN: Visualizing Basketball Trajectory and Analyzing Shooting Pose
- Automatically Overlaying Baseball Pitch Motion and Trajectory in Realtime (Open Source)
- Show HN: AI Basketball Analysis Web App and API
- Show HN: Visualize and Analyze Basketball Shots and Shooting Pose with ML
-
Ask HN: Show me your Half Baked project
I built an app to visualize and analyze basketball shots and shooting pose with machine learning.
https://github.com/chonyy/AI-basketball-analysis
The result is pretty nice. However, the only problem is the slow inference speed. I'm now refactoring the project structure and changing the model to a much faster YOLO model.
-
Show HN: Automatic Baseball Pitching Motion and Trajectory Overlay in Realtime
Thanks for asking! This is not a noob question.
I would say that the similar workflow could be applied to any ball-related sports. The object detection and the tracking algorithm is basically the same. Then, you could add any sport-specific feature!
For example, I have used a similar method to build AI Basketball Analysis.
https://github.com/chonyy/AI-basketball-analysis
- Show HN: AI Basketball Analysis in Realtime
- Show HN: AI Basketball Visualization
What are some alternatives?
Enzyme - High-performance automatic differentiation of LLVM and MLIR.
Deep-SORT-YOLOv4 - People detection and optional tracking with Tensorflow backend.
ForwardDiff.jl - Forward Mode Automatic Differentiation for Julia
openpifpaf - Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
Tullio.jl - ⅀
go-live - 🗂️ go-live is an ultra-light server utility that serves files, HTML or anything else, over HTTP.
TensorFlow.jl - A Julia wrapper for TensorFlow
veems - An open-source platform for online video.
Flux.jl - Relax! Flux is the ML library that doesn't make you tensor
FastMOT - High-performance multiple object tracking based on YOLO, Deep SORT, and KLT 🚀
InvertibleNetworks.jl - A Julia framework for invertible neural networks
SynthDet - SynthDet - An end-to-end object detection pipeline using synthetic data