Nnom

Visit Tool

nnom is a higher-level Neural Network library for microcontrollers that enables deployment of Keras models with a single line of code. It supports complex structures like Inception and ResNet, offering high-performance backend selections and onboard evaluation tools.

Claim this tool

No Views Yet

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is nnom?

NNoM is a high-level inference Neural Network library specifically designed for microcontrollers, aiming to provide a lightweight, user-friendly, and flexible interface for fast deployment on MCUs. It allows users to deploy Keras models to NNoM models with a single line of code and supports complex neural network structures such as Inception, ResNet, DenseNet, and Octave Convolution. The library features high-performance backend selections, including an optimized CMSIS-NN/DSP for ARM-Cortex-M, and onboard evaluation tools like runtime analysis and confusion matrix. NNoM manages structure and memory, simplifying embedded AI development. It is released under the Apache License 2.0.

Best used for

Ideal for embedded developers who need to deploy neural network models on microcontrollers, optimize inference time, and manage memory efficiently. Especially valuable for those working with Keras models and requiring high-performance, lightweight solutions for resource-constrained devices.

Common actions

deploy neural networks

optimize AI models

develop embedded AI

manage memory

automated workflowopen-sourcedeepfakecollaborationlow-code/no-codeface swapping"AI Agents"workflowsgithub copilot

Capabilities

Key features

Deploy Keras models
Support complex NN structures
High-performance backends
Onboard evaluation tools
Per-channel quantisation
Recurrent Layers (RNN)

Target Audience

developer

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What types of neural network structures does NNoM support?

NNoM supports a variety of complex neural network structures, including Inception, ResNet, DenseNet, and Octave Convolution. It also includes support for Recurrent Layers like Simple RNN, GRU, and LSTM, making it versatile for different AI applications on microcontrollers.

How does NNoM optimize performance on microcontrollers?

NNoM offers high-performance backend selections, including an optimized CMSIS-NN/DSP for ARM-Cortex-M4/7/33/35P, which can provide up to 5x performance improvement compared to the default C backend. It also features onboard pre-compiling to eliminate interpreter performance loss at runtime.

What are the TensorFlow version requirements for NNoM?

NNoM requires TensorFlow version <= 2.14. It's important to note that TensorFlow 2.14 supports Python up to version 3.11, but Python 3.12 is not currently supported. Users should ensure their TensorFlow and Python environments meet these specifications.

Can NNoM convert Keras models for deployment?

Yes, NNoM is designed to deploy Keras models to NNoM models with just one line of code. This simplifies the process for developers familiar with Keras, allowing them to quickly adapt their models for microcontroller environments.

Trending

Subcategories trending in Coding & Development

Open Source & Models DevOps & Infrastructure No-Code / Low-Code Testing & QA Backend & APIs Prompt Engineering

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce