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
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
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
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
Sometimes the data passing through Axon layers change type from f64 to f32 . Any workaround for this? (Like enforcing the data type throu...
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
Hi All,
I run my training model in livebook. In case I would like to train the same model several times with an, the output sometime bec...
New
Hey, I’m trying to make a model like this:
Axon.input("features", shape: {nil, 784})
|> Axon.reshape({:auto, 28, 28, 1})
|>...
New
When I run this block for the first time:
{:ok, model_info} = Bumblebee.load_model({:hf, "distilbert-base-uncased"}, architecture: :base...
New
Trending Over Three Years
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
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’ve just started learning Elixir few weeks ago and I really enjoy that language.
Currently, I’d like to start with machine lear...
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
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
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
I am slowly but surely making my way through learning about Neural Networks with Axon, but I did have this question. For some reason, my...
New
I would like to do something like the following:
input = Axon.input("input", shape: {prediction_days, 1})
model =
input
|> Axon....
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:
Sub Categories:
Popular Tags
- #ecto
- #liveview
- #troubleshooting
- #learning-elixir
- #library
- #deployment
- #erlang
- #testing
- #genserver
- #mix
- #absinthe
- #remote-other
- #otp
- #plug
- #how-to-question
- #macros
- #postgres
- #elixirconf
- #channels
- #exunit
- #discussion
- #code-sync
- #podcasts
- #javascript
- #onsite
- #dialyzer
- #docker
- #authentication
- #ai
- #umbrella
- #full-time-contract
- #podcasts-by-brainlid
- #ecto-query
- #blog-post
- #elixirconf-us
- #elixir-ls
- #phoenix_html
- #iex
- #graphql
- #genstage
- #websockets
- #supervisor
- #advent-of-code
- #distillery
- #processes
- #elixirconf-eu
- #api
- #forms
- #security
- #performance
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.
Error tracking, logs, uptime, and Just Enough APM. Built for developers.
Elixir, Erlang & BEAM conferences from Code Sync - join us in 2026!
Practical resources that improve the lives of professional developers.
Master modern tools, write cleaner code, and tackle real-world challenges.
Bringing learning, work and compliance together since 1987.
The team behind Membrane, Popcorn, LiveDebugger. Available for hire.
Courses that'll move you from confusion to "Aha, now I get it!"