Latest #axon Threads 
Igor Ostaptchenko, Detroit MI — Senior/Staff Elixir Engineer, 13 years on the BEAM (Remote US, UTC-5)
About me
I have been shipping Elixi...
New
I’ve been working on an open-source framework for training bots for Super Smash Bros. Melee in Elixir (ExPhil). Along the way I got thoro...
New
Hey everyone.
So i’ve been developing a model and it started as a straightforward logistic regression model and has evolved into a multi...
New
It seems like they were removed from 0.6.1 -> 0.7.0, but I can’t find anything written about this apart from issue 580 which simply sa...
New
My model expects multiple named inputs, that means that I need to pass the data as a map with each input name like this:
inputs = %{
"...
New
I have a model where one of the layers is an Axon embedding layer. I want to get that layer results instead of the model original output....
New
The dataset I’m trying to train with comes with a initial weight for each row. I would like to use it as the initial weights during train...
New
When I run this block for the first time:
{:ok, model_info} = Bumblebee.load_model({:hf, "distilbert-base-uncased"}, architecture: :base...
New
Context
I am experimenting with text embedding with the hope of implementing semantic similarity search inside a Phoenix application.
My...
New
Soothsayer is an Elixir library for time series forecasting, inspired by Facebook’s Prophet and NeuralProphet. It provides a flexible and...
New
This Week's Trending
This Month's Trending
This Year's Trending
Hi, I could not compile dependency :axon_onnx :
Mix.install([
{:axon, "~> 0.5"},
{:nx, "~> 0.5"},
{:exla, "~> 0.5"},
{:stb_imag...
New
Soothsayer is an Elixir library for time series forecasting, inspired by Facebook’s Prophet and NeuralProphet. It provides a flexible and...
New
I’ve been working on an open-source framework for training bots for Super Smash Bros. Melee in Elixir (ExPhil). Along the way I got thoro...
New
Last Three Year's Trending
Is there any list of hardware, i.e. GPU that is compatible with Nx/Axon/etc. (apologies if I missed this information)? Does the general “...
New
Hi,
wanted to do a sentiment analysis using Elixir. Problem: Bumblebee has that only for English text.
Therefore, tried to load a [mode...
New
Hello,
i am working right now alot with axon i am working on a lstm for my mastersthesis.
I was wondering if there is a nice way to set...
New
Hey all, i’m trying to train a classification model (Trying EXGBoost and KNN) To predict a packaging type based on order content.
My dat...
New
I managed to compile XLA on Jetson Nano platform with Cuda 10.2 of JetPack
And I’m compiling XLA 0.2 because latest version (0.3) is aba...
New
Context
I am experimenting with text embedding with the hope of implementing semantic similarity search inside a Phoenix application.
My...
New
Recently, I am investigating the possibility of building out a LLaMa2 70B system which needs to be able to scale to thousands of requests...
New
I posted the SO question here too: https://stackoverflow.com/questions/76301934/how-to-get-the-loss-history-using-elixirs-axon-library
B...
New
We are attempting to fine-tune a sentence transformer model and we’re getting an error when we run the Axon training loop. Our attempt ca...
New
I’m training simple feed forward Neural Networks on CPU and I often see the memory usage go up over 128GB of RAM.
Is this normal? The tr...
New
I trained a model last year that we still use in prod and I committed the code.
The model has >99% accuracy.
If I want to train the ...
New
I’ve been working on adding ControlNet support to bumblebee.
This picture shows how this works. Basically, a ControlNet is only the enco...
New
Hey folks,
I’m quite new to the ML world, as well as to Nx and Axon (although not necessarily to Elixir). I’ve been trying to follow som...
New
This topic is for keeping track of the current <span class="hashtag-icon-placeholder"></span>elixirfashionmlchallenge leaderboard.
5 E...
New
Sometimes the data passing through Axon layers change type from f64 to f32 . Any workaround for this? (Like enforcing the data type throu...
New
Trending Over Three Years
Hey all :wave:
I took me a bit more than 1 year but I finally managed to finish “Programming Machine Learning - From Coding to Deep Lear...
New
Hello, I have been trying to get Exla installed for use with Nx and Axon. I am running Ubuntu 20 and I have read through the instructions...
New
Hello,
Like many people on Earth, I’ve been trying to understand the transformer architecture. I translated the Python code in https://w...
New
Hello,
I’ve just started learning Elixir few weeks ago and I really enjoy that language.
Currently, I’d like to start with machine lear...
New
Hi everyone,
I just saw the talk about Axon by Sean Moriarity from ElixirConf 2022 (Youtube Video). In the Current Limitations section (...
New
Google Colab is a great resource to learn/practice machine learning. We can go to Google Colab rather than running an ML stack on our loc...
New
Hi, I am trying to evaluate trained model by calling Axon.build and then calling resulting predict_fn function multiple times (once for e...
New
Hi all,
I took a look around the Axon and Nx codebases trying to determine how a model can be saved to a file and later imported.
I am ...
New
I am really excited about Nx/Axon. Jose has done a few examples of the MNIST dataset but it moved a bit too quickly for my ML n00b self t...
New
Hello! I’m following the example here bumblebee/notebooks/fine_tuning.livemd at main · elixir-nx/bumblebee · GitHub for fine tuning the B...
New
Hello,
I am working through the examples in the new book, Machine Learning in Elixir and I am having an issue with poor accuracy in Chap...
New
Hey all :waving_hand:
I’m reading this book on machine learning. I’m trying to rewrite all the numpy/Keras examples with Nx/Axon and for...
New
I’ve published a challenge to the Elixir community to collectively iterate until we have State of the Art (SOTA) accuracy on the FashionM...
New
Hello everyone, I’ve been studying Nx for a while by now, and have been writing an article about it.
When analyzing its performance, I’v...
New
Tales of the M1 GPU is a very nicely written discussion of GPUs in general and the Apple M1 GPU in particular. It would be great if someo...
New
- Follow
- Join
- Shape
the conversation
Latest on Elixir Forum
Get money off!
The Pragmatic Bookshelf
35% off any eBook
Manning Publications
45% off any item
ElixirCasts
10% off for life
The Pragmatic Studio
20% off any course
AppSignal
10% off for 12 months
Honeybadger
10% off for 12 months
Simply use coupon code "devtalk.com" or "elixirforum" at checkout!
Filter by Type:
Popular Tags
- #ecto
- #liveview
- #troubleshooting
- #learning-elixir
- #deployment
- #library
- #erlang
- #testing
- #genserver
- #mix
- #absinthe
- #remote-other
- #otp
- #plug
- #how-to-question
- #macros
- #postgres
- #channels
- #elixirconf
- #exunit
- #discussion
- #code-sync
- #javascript
- #podcasts
- #onsite
- #dialyzer
- #docker
- #authentication
- #umbrella
- #full-time-contract
- #podcasts-by-brainlid
- #ecto-query
- #elixir-ls
- #blog-post
- #phoenix_html
- #iex
- #ai
- #graphql
- #genstage
- #elixirconf-us
- #websockets
- #supervisor
- #advent-of-code
- #distillery
- #processes
- #api
- #forms
- #metaprogramming
- #security
- #hex
Forums
Our Sponsors
Build Elixir applications with speed and confidence.
Supporting innovation across the BEAM ecosystem.
We build reliable cloud platforms for business-critical systems.
Catch errors, track performance, monitor hosts and more.
Error tracking, logs, uptime, and Just Enough APM. Built for developers.
Develop your skills with books, videos, and courses.
Bringing learning, work and compliance together since 1987.
Enabling companies to succeed by building software people love.
The team behind Membrane, Popcorn, LiveDebugger. Available for hire.
Courses that'll move you from confusion to "Aha, now I get it!"