jax

Model description

I would like to add a new model:

Proposed in the paper: UNETR: Transformers for 3D Medical Image Segmentation

UNEt TRansformers (UNETR) utilize a transformer as the encoder to learn sequence representations of the input volume and effectively capture the global multi-scale information, while also following the successful "U-shaped"

It would be great if you could add the JAX equivalent of scipy.stats.mode, which is currently unavailable.

A use case may be a ML classification task with ensembles, where multiple models give different predictions, and we are interested in finding the most common one.

As an example, consider predictions to be a two-dimensional DeviceArray of predictions, with
shape = (number of model

Is there a way to train a bidirectional RNN (like LSTM or GRU) on trax nowadays?

Love the book! Ran into this display issue when viewing it on Chrome's PDF viewer:

A quick search for mixture distributions in numpyro only turns up examples using Categorical in conjunction with an array of distributions. Since sampling from discrete distributions is not always desirable, I have implemented a quick general purpose mixture distribution with continuous log probability.

class Mixture(Distribution):
    arg_constraints = {}

    def __init__(self

Dear Brax team,

Since Brax is fully differentiable, I thought it'd be possible to use it like DiffTaichi or GradSim for system identification (e.g. determining the mass of an object from a trajectory and known force) but I couldn't find any example for this.
Do you happen to have any demo or tips for this?

From the top of my head I would do something like this:
Let's say the task is to es

these are the examples on docs/notebooks/

Probably it's necessary to add this line when running on TPUs https://github.com/google/jax#pip-installation-colab-tpu

I think this would be a good first issue