C# library for easy Deep Learning and Deep Reinforcement Learning. It is wrapper over C# CNTK API. Has implementation of layers (LSTM, Convolution etc.), optimizers, losses, shortcut-connections, sequential model, sequential multi-output model, agent teachers, policy gradients, actor-critic etc.
Contains helpers for work with dataset (split, statistics, SMOTE etc).
Allows train, evaluate and inference deep neural networks in style similar to Keras.
See the version list below for details.
Install-Package EasyCNTK -Version 0.4.0
dotnet add package EasyCNTK --version 0.4.0
<PackageReference Include="EasyCNTK" Version="0.4.0" />
paket add EasyCNTK --version 0.4.0
Add model with multi outputs
Add PolicyGradietns agent teacher (Reinforcement Learning)
Add Actor-Critic agent teacher (Reinforcement Learning)
Small change public API for predict and fit methods (!!!)
This package is not used by any popular GitHub repositories.