jax
Here are 173 public repositories matching this topic...
Numpy has a very convenient np.mgrid which allow to easily create coordinate grids: https://numpy.org/doc/stable/reference/generated/numpy.mgrid.html.
I was expecting jax to have the same, but it seems to be missing:
jnp.mgrid # raise AttributeErrorTracking implementation of these:
-
jnp.mgrid#6248 -
jnp.ogrid#6342 -
jnp.r_#6593 - `j
Bidirectional RNN
Is there a way to train a bidirectional RNN (like LSTM or GRU) on trax nowadays?
-
Updated
Jul 23, 2021 - Python
-
Updated
Jun 6, 2021 - Python
-
Updated
Jul 23, 2021 - Python
-
Updated
Jul 19, 2021 - Python
-
Updated
Jul 22, 2021 - Python
-
Updated
Jul 6, 2021 - Python
-
Updated
Jun 29, 2021 - Jupyter Notebook
-
Updated
Jul 20, 2021 - Python
-
Updated
Jun 18, 2021 - Python
Having trace.format_shapes() as in Pyro would help with debugging and verifying models, especially with enumeration, as shown in the Pyro tutorial.
-
Updated
Jul 23, 2021 - Python
-
Updated
Jul 19, 2021 - Python
-
Updated
Jul 22, 2021 - Jupyter Notebook
-
Updated
Jul 2, 2021 - Python
-
Updated
Jul 20, 2021
-
Updated
Apr 8, 2021 - Jupyter Notebook
-
Updated
Jul 28, 2020 - Python
-
Updated
Jun 11, 2021 - Python
-
Updated
Jul 16, 2021 - Python
-
Updated
Jul 13, 2021 - Python
-
Updated
Jul 21, 2021 - Jupyter Notebook
Description
TIL that pip has a super nice Issue template page
that uses a [.github/ISSUE_TEMPLATE/config.yml](https://github.com/pypa/pip/blob/e6414d6db6db37951988f6f2b11ec530ed0b191d/.github/ISSUE_TEMPLATE/conf
See wikipedia table for example patterns: https://en.wikipedia.org/wiki/List_of_integrals_of_Gaussian_functions
-
Updated
Oct 21, 2020 - Python
-
Updated
Dec 15, 2020 - Python
-
Updated
Apr 5, 2021 - 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."

Add better error message to
HubertForCTC,Wav2Vec2ForCTCif labels are bigger than vocab size.Motivation
Following this issue: huggingface/transformers#12264 it is clear that an error message should be thrown if any of the any of the labels are >
self.config.vocab_sizeor else silent errors can sneak into the training script.So w