Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A TensorFlow-inspired neural network library built from scratch in C# 7.3 for .NET Standard 2.0, with GPU support through cuDNN
| Date | Stars |
|---|---|
| 2026-07-31 | 573 |
| 2026-08-01 | 573 |
| 2026-08-02 | 573 |
| 2026-08-06 | 573 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<a href="https://www.nuget.org/packages/NeuralNetwork.NET/"><img src="https://user-images.githubusercontent.com/10199417/66045292-b5e7e380-e523-11e9-96f8-6fb4c4df52c3.png" alt="Get it from NuGet" width='620' height='186' /></a> <a href="https://scisharp.github.io/SciSharp/"><img src="https://github.com/SciSharp/SciSharp/raw/master/art/scisharp_badge.png" alt="ScuSharp STACK" width='186' height='186' /></a>
[](https://www.nuget.org/packages/NeuralNetwork.NET/) [](https://www.nuget.org/stats/packages/NeuralNetwork.NET?groupby=Version) [](https://ci.appveyor.com/project/Sergio0694/neuralnetwork-net/master) [](https://ci.appveyor.com/project/Sergio0694/neuralnetwork-net/master) [](https://twitter.com/SergioPedri)
# What is it?
**NeuralNetwork.NET** is a .NET Standard 2.0 library that implements sequential and computation graph neural networks with customizable layers, built from scratch with C#.
It provides simple APIs designed for quick prototyping to define and train models using stochastic gradient descent, as well as methods to save/load a network model and its metadata and more. The library also exposes CUDA-accelerated layers with more advanced features that leverage the GPU and the cuDNN toolkit to greatly increase the performances when training or using a neural network.
> **DISCLAIMER:** this library is provided as is, and it's no longer being actively maintained. NeuralNetwork.NET was developed during a university course and it's not meant to be a replacement for other well known machine learning frameworks. If you're looking for a machine learning library for .NET to use in production, I recommend trying out [ML.NET](https://dotnet.microsoft.com/apps/machinelearning-ai/ml-dotnet) or alternatively [TensorFlow.NET](https://github.com/SciSharp/TensorFlow.NET).
# Table of Contents
- [Installing from NuGet](#installing-from-nuget)
- [Quick start](#quick-start)
- [Supervised learning](#supervised-learning)
- [GPU acceleration](#gpu-acceleration)
- [Computation graphs](#computation-graphs)
- [Library settings](#library-settings)
- [Serialization and deserialization](#serialization-and-deserialization)
- [Built-in datasets](#built\-in-datasets)
- [Requirements](#requirements)
# Installing from NuGet
To install **NeuralNetwork.NET**, run the following command in the **Package Manager Console**
```
Install-Package NeuralNetwork.NET
```
More details available [here](https://www.nuget.org/packages/NeuralNetwork.NET/).
# Quick start
The **NeuralNetwork.NET** library exposes easy to use classes and methods to create a new neural network, prepare the datasets to use and train the network. These APIs are designed for rapid prototyping, and this section provides an overview of the required steps to get started.
## Supervised learning
The first step is to create a custom network structure. Here is an example with a sequential network (a stack of layers):
```C#
INeuralNetwork network = NetworkManager.NewSequential(TensorInfo.Image<Alpha8>(28, 28),
NetworkLayers.Convolutional((5, 5), 20, ActivationType.Identity),
NetworkLayers.Pooling(ActivationType.LeakyReLU),
NetworkLayers.Convolutional((3, 3), 40, ActivationType.Identity),
NetworkLayers.Pooling(ActivationType.LeakyReLU),
NetworkLayers.FullyConnected(125, ActivationType.LeakyReLU),
NetworkLayers.FullyConnected(64, ActivationType.LeakyReLU),
NetworkLayers.Softmax(10));
```
The next step is to prepare the datasets to use, through the APIs in the `DatasetLoader` class:
```C#
// A training dataset with a batch size of 100
IEnumerable<(floaExcerpt of 11,959 characters
Read on GitHub
802
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1dc7bc1c225bd8ed, topic:cuda
matched fp:1dc7bc1c225bd8ed, topic:neural-network