AI Mathematics + Tensor Operations Toolkit built on JAX
Project description
Jux-Numpy 🚀
Jux-Numpy is an AI mathematics and tensor operations toolkit built on top of JAX.
Features
- AI Math operations (entropy, KL divergence, mutual information)
- ML metrics (MAE, MSE, RMSE)
- Probability tools (softmax, entropy)
- Vector similarity tools (cosine, euclidean)
- JAX-powered performance backend
Example
import jux_numpy as jux
x = jux.array([1,2,3])
y = jux.softmax(x)
print(y)
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
jux_numpy-0.1.0.tar.gz
(7.3 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file jux_numpy-0.1.0.tar.gz.
File metadata
- Download URL: jux_numpy-0.1.0.tar.gz
- Upload date:
- Size: 7.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f167845fe497919064d7af180dcce1b99dbf72334b78f16d0d7fc27ab42501e8
|
|
| MD5 |
64cc8ffe279fe971013d0cd961d26171
|
|
| BLAKE2b-256 |
ba7dc02cc692b182a903e92b02b458801c4d71835449d9397d9b0f6cddad245f
|
File details
Details for the file jux_numpy-0.1.0-py3-none-any.whl.
File metadata
- Download URL: jux_numpy-0.1.0-py3-none-any.whl
- Upload date:
- Size: 8.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bd04324affd3edd7612179cd893cb83ee4969ce2315894e57e7f8f5acf8a59c7
|
|
| MD5 |
5b11f41047c2e0ddbcb9c0db6930be15
|
|
| BLAKE2b-256 |
ed4051dbb3d7b2e0e5f4fd97c6d2f42374462bac316c180ff41154655de4d585
|
