jax
Here are 269 public repositories matching this topic...
>>> lax.broadcast_shapes((-1,), (1,))
(-1,)
>>> np.broadcast_shapes((-1,), (1,))
------------------------------------------------------------------------Bidirectional RNN
Is there a way to train a bidirectional RNN (like LSTM or GRU) on trax nowadays?
-
Updated
Feb 11, 2022 - Python
-
Updated
Feb 17, 2022 - Python
Display Issues
-
Updated
Feb 24, 2022 - Python
-
Updated
Feb 25, 2022 - Python
-
Updated
Feb 25, 2022 - Python
-
Updated
Feb 12, 2022 - Python
-
Updated
Feb 24, 2022 - Python
-
Updated
Feb 24, 2022 - Jupyter Notebook
This will help some forum users avoid issues like using HalfNormal(loc, scale) for HalfNormal distribution. In such case, validate_args will take the value of scale (because HalfNormal does not have loc parameter) and raise some misleading errors.
-
Updated
Feb 10, 2022 - Python
-
Updated
Feb 24, 2022 - Python
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
-
Updated
Feb 24, 2022 - Python
-
Updated
Feb 7, 2022 - Python
-
Updated
Feb 24, 2022 - Python
-
Updated
Dec 13, 2021 - Jupyter Notebook
-
Updated
Feb 9, 2022 - Python
-
Updated
Feb 25, 2022 - Python
-
Updated
Feb 24, 2022
-
Updated
Aug 26, 2021 - Jupyter Notebook
jit and unroll don't seem to be documented in https://jaxopt.github.io/stable/_autosummary/jaxopt.GradientDescent.html#jaxopt-gradientdescent
-
Updated
Aug 30, 2021 - Python
-
Updated
Jul 28, 2020 - Python
-
Updated
Feb 20, 2022 - Python
-
Updated
Feb 25, 2022 - Python
Improve this page
Add a description, image, and links to the jax topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the jax topic, visit your repo's landing page and select "manage topics."

Hello,
The code says that it will add compatibility for Postponed Evaluation of Annotations (PEP 563) when Python 3.9 is released (which already happened on 2020.10.5). Is there any plan to complete this?
https://github.com/huggingface/transformers/blob/2c2a31ffbcfe03339b1721348781aac4fc05bc5e/src/transformers/hf_argparser.py#L85-L90