Tyill/sunnet
tiny neural net
This is a lightweight deep learning library designed for machine learning engineers and developers who build and deploy neural networks. It takes raw data, processes it through defined network architectures, and produces trained models or inference results. You would use this if you need to integrate neural network capabilities into applications, especially in environments where resource efficiency is critical.
No commits in the last 6 months.
Use this if you need a flexible, resource-efficient library to implement and deploy neural networks in C++, C#, or Python, particularly for tasks like image classification or other predictive modeling where performance and memory footprint are important.
Not ideal if you are a data scientist primarily focused on high-level model experimentation and rapid prototyping with extensive pre-built functionality and a large ecosystem.
Stars
62
Forks
24
Language
C++
License
MIT
Category
Last pushed
Aug 15, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Tyill/sunnet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Dobiasd/frugally-deep
A lightweight header-only library for using Keras (TensorFlow) models in C++.
flashlight/flashlight
A C++ standalone library for machine learning
wichtounet/dll
Fast Deep Learning Library (DLL) for C++ (ANNs, CNNs, RBMs, DBNs...)
NVlabs/tiny-cuda-nn
Lightning fast C++/CUDA neural network framework
KasperskyLab/knp
Kaspersky Neuromorphic Platform