Stergios
Stergios
Solves #1696 Adds the following: - `entropy` method for: Bernoulli/Categorical/DiscreteUniform/Geometric - `mode` property for: Bernoulli/Categorical/Binomial/Poisson/Geometric - `name` property for all distributions and explanation for NotImplementedError. Current Status: Passes all local...
The following explains the issue. ```python import distrax import numpyro as pyro import jax.numpy as jnp import jax.random as jrandom import tensorflow_probability.substrates.jax as tfp import matplotlib.pyplot as plt key =...
Hello guys, I come from the Tensorflow Distributions world and was looking for a lightweight alternative and was pleasantly surprised to see that Pyro is available for Jax via your...
Hello Patrick, again thank you for the nice package. I wanted to ask whether there exists a way to deserialise an Equinox-trained model (in eqx format [json+bytes]) to be used...
Hey Patrick, I have been using Equinox for one of my projects and up until now it has helped immensely in using JAX effectively and seamlessly. For this project, I...
Hello Patrick, I am doing an implementation of the PPO algorithm for a custom environment and first wanted to test things out with a standard example and I choose CartPole-v1...
The Jax pip installation only comes with the CPU version of Jax. Is this intended? ```pip install adam-robotics[jax]```
Greetings Patrick, I was wondering, what are your thoughts when it comes to Graph Neural Networks? Would a GNNlayer be implemented as a module for Equinox or an advanced example...
### Description Hey Jax team thanks for the amazing work you are all doing with this project. I am working with Jax for quite sometime now and ever since the...
There seems to be a race to find the best implementation (currently 4) of KANs on the PyTorch side of the ML universe but there is a dearth of efforts...