Skip to main content

Neural Operators in JAX

Project description

neojax

[!WARNING] Work in Progress: This project is in its early stages of development and is currently not functional. It is being shared for development and architectural purposes only.

This is neojax (Neural Operators in jax), a port of the popular neural operators pytorch library to jax. It is built on top of jax and equinox and provides the same API as the original pytorch library.

Installation

Install the python package via pypi

pip3 install neojax-operators

Quickstart

neojax exposes the same API as neuraloperators and can therefore be used as a drop-in replacement:

from neojax.models import FNO
operator = FNO(n_modes=(64, 64),
               hidden_channels=64,
               in_channels=2,
               out_channels=1)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

neojax_operators-0.0.2.tar.gz (604.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

neojax_operators-0.0.2-py3-none-any.whl (13.4 kB view details)

Uploaded Python 3

File details

Details for the file neojax_operators-0.0.2.tar.gz.

File metadata

  • Download URL: neojax_operators-0.0.2.tar.gz
  • Upload date:
  • Size: 604.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for neojax_operators-0.0.2.tar.gz
Algorithm Hash digest
SHA256 a6b6a2b6a70aec7705948ec9c51cc31eaf620dfb35a1afcc261b6528a7f77e9f
MD5 720fc9d2b4353a9b546172ec7833b3e2
BLAKE2b-256 105d13d45d86de7848d3ad04019d28b6934e34cb5bcadbac49616a578af12c66

See more details on using hashes here.

File details

Details for the file neojax_operators-0.0.2-py3-none-any.whl.

File metadata

File hashes

Hashes for neojax_operators-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 a728870852e9d720d2526e334488b800d84fba80d1760a6b15d7af0052024a41
MD5 476b2996bd27512f5879268aef5fcda3
BLAKE2b-256 284c5bea6a8f16719170f429ce3c6b0dcb6f427a00cb860df56c215efbddaa6b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page