Skip to main content

Inferno Header

Inferno is an extensible library for simulating spiking neural networks. Built on top of PyTorch, it is designed with machine learning practitioners in mind. This project is still an early release and features may be subject to change.

Installation

At this time, installation is only supported via pip. Future support for installation with conda is planned.

With PyTorch (CPU Only)

pip install inferno-ai[torch]

Installation with the "torch" flag will install PyTorch 2.4.1 and the corresponding version of TorchVision.

Without PyTorch

pip install inferno-ai

Note: Inferno still requires PyTorch and a version of it must be installed. PyTorch will need to be installed separately if CUDA support is required. See the instructions for installing PyTorch for details.

Getting Started

For an example of walking through building, training, and evaluating a spiking neural network, see the quickstart example. A comprehensive documentation of the classes and functions provided by Inferno are available here.

Metadata

Release files for inferno-ai 0.0.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for inferno-ai 0.0.5
File Size Uploaded
inferno_ai-0.0.5.tar.gz 128.3 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for inferno-ai 0.0.5
File Interpreter ABI Platform
inferno_ai-0.0.5-py3-none-any.whl Python 3 none any Details

Total release size: 303.2 kB

Release files / inferno_ai-0.0.5.tar.gz

Download URL inferno_ai-0.0.5.tar.gz
Size 128.3 kB
Tags Source
SHA-256 checksum
How to use checksums
335f729aa5de0ed7b8cbc1b74c9983c3fce1756f65853256d44bbe63378c4cc5
BLAKE2b-256 checksum
How to use checksums
5fae13889b05b54e013c603d62aa250d036070d37f2057355029741464b1fe1e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.1 CPython/3.11.9

Release files / inferno_ai-0.0.5-py3-none-any.whl

Download URL inferno_ai-0.0.5-py3-none-any.whl
Size 174.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
bc371eca7a9bedd2b2c121f23600dc73e57020ebc953f6139fc78f8b2a794410
BLAKE2b-256 checksum
How to use checksums
89d5bf901e2287ac34f9b1e0a41803118c60823c00ae938f5326bb9000c5c2fb
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.1 CPython/3.11.9

Release history Release notifications | RSS feed

This release

0.0.5 This release

2 release files

0.0.4

2 release files

0.0.3

2 release files

0.0.2

2 release files

0.0.1

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page